< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3032 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.4510. Min Act: -0.1700

Data Index: 6976087 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.4185. Min Act: -0.1700

Data Index: 9797126 (The Pile)

Max Activating Token Index: 1021

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.3368. Min Act: -0.1700

Data Index: 2452114 (The Pile)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.3204. Min Act: -0.1700

Data Index: 3386399 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.3040. Min Act: -0.1700

Data Index: 1198870 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2875. Min Act: -0.1700

Data Index: 1954881 (The Pile)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2711. Min Act: -0.1700

Data Index: 2356236 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2711. Min Act: -0.1700

Data Index: 10401222 (The Pile)

Max Activating Token Index: 917

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2711. Min Act: -0.1700

Data Index: 5220101 (The Pile)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2711. Min Act: -0.1700

Data Index: 7342685 (The Pile)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2711. Min Act: -0.1700

Data Index: 1255062 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2711. Min Act: -0.1700

Data Index: 5880528 (The Pile)

Max Activating Token Index: 450

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2711. Min Act: -0.1700

Data Index: 6709179 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2546. Min Act: -0.1700

Data Index: 3853494 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2546. Min Act: -0.1700

Data Index: 1271425 (The Pile)

Max Activating Token Index: 350

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2546. Min Act: -0.1700

Data Index: 8008139 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2546. Min Act: -0.1700

Data Index: 3619124 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2380. Min Act: -0.1700

Data Index: 1376697 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2380. Min Act: -0.1700

Data Index: 3496113 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.4510. Min Range: -2.4510

Max Act: 2.2380. Min Act: -0.1700

Data Index: 7590723 (The Pile)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #19