< Prev | Home | Model | Random | Next >

Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer

Dataset: Open Web Text

Neuron 4 in Layer 21

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')



Text #0

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.7359. Min Act: -0.1700

Data Index: 5668574 (Open Web Text)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.6422. Min Act: -0.1700

Data Index: 1627677 (Open Web Text)

Max Activating Token Index: 550

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.6422. Min Act: -0.1700

Data Index: 8623937 (Open Web Text)

Max Activating Token Index: 439

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.6734. Min Act: -0.1700

Data Index: 1916292 (Open Web Text)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.5484. Min Act: -0.1700

Data Index: 1277547 (Open Web Text)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.5172. Min Act: -0.1700

Data Index: 3035414 (Open Web Text)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.5172. Min Act: -0.1700

Data Index: 7879013 (Open Web Text)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.5172. Min Act: -0.1700

Data Index: 4871383 (Open Web Text)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.4859. Min Act: -0.1700

Data Index: 6999530 (Open Web Text)

Max Activating Token Index: 615

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.4547. Min Act: -0.1700

Data Index: 1074381 (Open Web Text)

Max Activating Token Index: 220

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.4547. Min Act: -0.1700

Data Index: 1085126 (Open Web Text)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.4234. Min Act: -0.1700

Data Index: 5026039 (Open Web Text)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.4234. Min Act: -0.1700

Data Index: 2790445 (Open Web Text)

Max Activating Token Index: 311

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.3922. Min Act: -0.1700

Data Index: 8048357 (Open Web Text)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.4234. Min Act: -0.1700

Data Index: 4587329 (Open Web Text)

Max Activating Token Index: 558

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.3922. Min Act: -0.1700

Data Index: 3088288 (Open Web Text)

Max Activating Token Index: 745

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.3922. Min Act: -0.1700

Data Index: 338209 (Open Web Text)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.3297. Min Act: -0.1700

Data Index: 1641312 (Open Web Text)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.3297. Min Act: -0.1700

Data Index: 71769 (Open Web Text)

Max Activating Token Index: 126

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.7359. Min Range: -4.7359

Max Act: 4.2984. Min Act: -0.1700

Data Index: 648079 (Open Web Text)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #19