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

Dataset: The Pile

Neuron 3621 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: 1.6486. Min Range: -1.6486

Max Act: 1.6486. Min Act: -0.0000

Data Index: 98027 (The Pile)

Max Activating Token Index: 499

Text #1

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.3190. Min Act: -0.0000

Data Index: 185929 (The Pile)

Max Activating Token Index: 984

Text #2

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.2962. Min Act: -0.0000

Data Index: 1484933 (The Pile)

Max Activating Token Index: 579

Text #3

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1729243 (The Pile)

Max Activating Token Index: 805

Text #4

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1464. Min Act: -0.0000

Data Index: 1883336 (The Pile)

Max Activating Token Index: 561

Text #5

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1597. Min Act: -0.0000

Data Index: 1902264 (The Pile)

Max Activating Token Index: 230

Text #6

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1804. Min Act: -0.0000

Data Index: 633202 (The Pile)

Max Activating Token Index: 532

Text #7

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1174. Min Act: -0.0000

Data Index: 60858 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1836. Min Act: -0.0000

Data Index: 324332 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1131. Min Act: -0.0000

Data Index: 1381006 (The Pile)

Max Activating Token Index: 553

Text #10

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1032. Min Act: -0.0000

Data Index: 1371164 (The Pile)

Max Activating Token Index: 253

Text #11

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1048. Min Act: -0.0000

Data Index: 752872 (The Pile)

Max Activating Token Index: 651

Text #12

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0586. Min Act: -0.0000

Data Index: 111726 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0527. Min Act: -0.0000

Data Index: 594093 (The Pile)

Max Activating Token Index: 883

Text #14

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0969. Min Act: -0.0000

Data Index: 1861865 (The Pile)

Max Activating Token Index: 154

Text #15

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.1129. Min Act: -0.0000

Data Index: 1962139 (The Pile)

Max Activating Token Index: 988

Text #16

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0194. Min Act: -0.0000

Data Index: 789510 (The Pile)

Max Activating Token Index: 953

Text #17

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0359. Min Act: -0.0000

Data Index: 605769 (The Pile)

Max Activating Token Index: 58

Text #18

Max Range: 1.6486. Min Range: -1.6486

Max Act: 0.9535. Min Act: -0.0000

Data Index: 1943668 (The Pile)

Max Activating Token Index: 527

Text #19

Max Range: 1.6486. Min Range: -1.6486

Max Act: 1.0195. Min Act: -0.0000

Data Index: 1277485 (The Pile)

Max Activating Token Index: 27