< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1102 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.5193. Min Act: -0.1700

Data Index: 4389378 (The Pile)

Max Activating Token Index: 521

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.5436. Min Act: -0.1700

Data Index: 6044949 (The Pile)

Max Activating Token Index: 634

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4951. Min Act: -0.1700

Data Index: 6134510 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4707. Min Act: -0.1700

Data Index: 9846108 (The Pile)

Max Activating Token Index: 807

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4870. Min Act: -0.1700

Data Index: 8731167 (The Pile)

Max Activating Token Index: 248

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4870. Min Act: -0.1700

Data Index: 3422380 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4707. Min Act: -0.1700

Data Index: 7336381 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4545. Min Act: -0.1700

Data Index: 3411002 (The Pile)

Max Activating Token Index: 883

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4464. Min Act: -0.1700

Data Index: 2701504 (The Pile)

Max Activating Token Index: 469

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4870. Min Act: -0.1700

Data Index: 9259601 (The Pile)

Max Activating Token Index: 866

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4301. Min Act: -0.1700

Data Index: 1952390 (The Pile)

Max Activating Token Index: 441

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4464. Min Act: -0.1700

Data Index: 8329416 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4301. Min Act: -0.1700

Data Index: 9892946 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4383. Min Act: -0.1700

Data Index: 7518254 (The Pile)

Max Activating Token Index: 534

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4383. Min Act: -0.1700

Data Index: 2041926 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4220. Min Act: -0.1700

Data Index: 9945424 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4220. Min Act: -0.1700

Data Index: 7891198 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4138. Min Act: -0.1700

Data Index: 8966287 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4301. Min Act: -0.1700

Data Index: 10043666 (The Pile)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5436. Min Range: -2.5436

Max Act: 2.4138. Min Act: -0.1700

Data Index: 4503366 (The Pile)

Max Activating Token Index: 802

Click toggle to see full text

Truncated

Full Text #19