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

Dataset: The Pile

Neuron 3926 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.3136. Min Act: -0.0000

Data Index: 527159 (The Pile)

Max Activating Token Index: 662

Text #1

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1842. Min Act: -0.0000

Data Index: 608460 (The Pile)

Max Activating Token Index: 855

Text #2

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1516. Min Act: -0.0000

Data Index: 47115 (The Pile)

Max Activating Token Index: 484

Text #3

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1409. Min Act: -0.0000

Data Index: 1942665 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.1121. Min Act: -0.0000

Data Index: 1257419 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0981. Min Act: -0.0000

Data Index: 1045494 (The Pile)

Max Activating Token Index: 985

Text #6

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0379. Min Act: -0.0000

Data Index: 1073769 (The Pile)

Max Activating Token Index: 79

Text #7

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0418. Min Act: -0.0000

Data Index: 839189 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0251. Min Act: -0.0000

Data Index: 1523408 (The Pile)

Max Activating Token Index: 745

Text #9

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9585. Min Act: -0.0000

Data Index: 896267 (The Pile)

Max Activating Token Index: 623

Text #10

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0687. Min Act: -0.0000

Data Index: 1241022 (The Pile)

Max Activating Token Index: 881

Text #11

Max Range: 1.3136. Min Range: -1.3136

Max Act: 1.0164. Min Act: -0.0000

Data Index: 1006166 (The Pile)

Max Activating Token Index: 433

Text #12

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8770. Min Act: -0.0000

Data Index: 1616497 (The Pile)

Max Activating Token Index: 231

Text #13

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9598. Min Act: -0.0000

Data Index: 1649805 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9184. Min Act: -0.0000

Data Index: 327821 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9659. Min Act: -0.0000

Data Index: 967076 (The Pile)

Max Activating Token Index: 33

Text #16

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.8425. Min Act: -0.0000

Data Index: 361033 (The Pile)

Max Activating Token Index: 58

Text #17

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9070. Min Act: -0.0000

Data Index: 412134 (The Pile)

Max Activating Token Index: 835

Text #18

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9126. Min Act: -0.0000

Data Index: 1974133 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 1.3136. Min Range: -1.3136

Max Act: 0.9178. Min Act: -0.0000

Data Index: 178931 (The Pile)

Max Activating Token Index: 627