Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 4058 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9365. Min Act: -0.0000

Data Index: 1335351 (The Pile)

Max Activating Token Index: 987

Text #1

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9433. Min Act: -0.0000

Data Index: 37975 (The Pile)

Max Activating Token Index: 73

Text #2

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9064. Min Act: -0.0000

Data Index: 1126636 (The Pile)

Max Activating Token Index: 591

Text #3

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.9472. Min Act: -0.0000

Data Index: 1425339 (The Pile)

Max Activating Token Index: 300

Text #4

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8362. Min Act: -0.0000

Data Index: 1938121 (The Pile)

Max Activating Token Index: 521

Text #5

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8126. Min Act: -0.0000

Data Index: 59469 (The Pile)

Max Activating Token Index: 991

Text #6

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8176. Min Act: -0.0000

Data Index: 75607 (The Pile)

Max Activating Token Index: 378

Text #7

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7958. Min Act: -0.0000

Data Index: 967150 (The Pile)

Max Activating Token Index: 690

Text #8

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8177. Min Act: -0.0000

Data Index: 141089 (The Pile)

Max Activating Token Index: 1012

Text #9

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8113. Min Act: -0.0000

Data Index: 356792 (The Pile)

Max Activating Token Index: 279

Text #10

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8323. Min Act: -0.0000

Data Index: 101883 (The Pile)

Max Activating Token Index: 331

Text #11

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1816519 (The Pile)

Max Activating Token Index: 161

Text #12

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8026. Min Act: -0.0000

Data Index: 1599948 (The Pile)

Max Activating Token Index: 317

Text #13

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1870133 (The Pile)

Max Activating Token Index: 408

Text #14

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1198793 (The Pile)

Max Activating Token Index: 116

Text #15

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7990. Min Act: -0.0000

Data Index: 1028354 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1334678 (The Pile)

Max Activating Token Index: 554

Text #17

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7825. Min Act: -0.0000

Data Index: 275471 (The Pile)

Max Activating Token Index: 1007

Text #18

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1779040 (The Pile)

Max Activating Token Index: 198

Text #19

Max Range: 0.9472. Min Range: -0.9472

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1725094 (The Pile)

Max Activating Token Index: 559