Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 4339 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4990. Min Act: -0.0000

Data Index: 1737855 (The Pile)

Max Activating Token Index: 211

Text #1

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.4875. Min Act: -0.0000

Data Index: 432032 (The Pile)

Max Activating Token Index: 386

Text #2

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3714. Min Act: -0.0000

Data Index: 746338 (The Pile)

Max Activating Token Index: 100

Text #3

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3408. Min Act: -0.0000

Data Index: 1486832 (The Pile)

Max Activating Token Index: 348

Text #4

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3419. Min Act: -0.0000

Data Index: 1464657 (The Pile)

Max Activating Token Index: 283

Text #5

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3185. Min Act: -0.0000

Data Index: 1307909 (The Pile)

Max Activating Token Index: 861

Text #6

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3024. Min Act: -0.0000

Data Index: 419957 (The Pile)

Max Activating Token Index: 383

Text #7

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.3310. Min Act: -0.0000

Data Index: 1101493 (The Pile)

Max Activating Token Index: 180

Text #8

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.1022. Min Act: -0.0000

Data Index: 296269 (The Pile)

Max Activating Token Index: 710

Text #9

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.0777. Min Act: -0.0000

Data Index: 578037 (The Pile)

Max Activating Token Index: 698

Text #10

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.2263. Min Act: -0.0000

Data Index: 1739996 (The Pile)

Max Activating Token Index: 997

Text #11

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.2378. Min Act: -0.0000

Data Index: 471728 (The Pile)

Max Activating Token Index: 606

Text #12

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.1880. Min Act: -0.0000

Data Index: 845043 (The Pile)

Max Activating Token Index: 628

Text #13

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.2452. Min Act: -0.0000

Data Index: 620145 (The Pile)

Max Activating Token Index: 284

Text #14

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.2030. Min Act: -0.0000

Data Index: 1696925 (The Pile)

Max Activating Token Index: 703

Text #15

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.2005. Min Act: -0.0000

Data Index: 316250 (The Pile)

Max Activating Token Index: 37

Text #16

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.2398. Min Act: -0.0000

Data Index: 275970 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.1194. Min Act: -0.0000

Data Index: 1158368 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.1758. Min Act: -0.0000

Data Index: 1379145 (The Pile)

Max Activating Token Index: 418

Text #19

Max Range: 1.4990. Min Range: -1.4990

Max Act: 1.1771. Min Act: -0.0000

Data Index: 889363 (The Pile)

Max Activating Token Index: 95