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

Dataset: The Pile

Neuron 1385 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: 0.3339. Min Range: -0.3339

Max Act: 0.3296. Min Act: -0.0000

Data Index: 752234 (The Pile)

Max Activating Token Index: 1012

Text #1

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.3339. Min Act: -0.0000

Data Index: 1506838 (The Pile)

Max Activating Token Index: 925

Text #2

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2912. Min Act: -0.0000

Data Index: 703258 (The Pile)

Max Activating Token Index: 933

Text #3

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2239. Min Act: -0.0000

Data Index: 1265648 (The Pile)

Max Activating Token Index: 483

Text #4

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2418. Min Act: -0.0000

Data Index: 1064988 (The Pile)

Max Activating Token Index: 925

Text #5

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2429. Min Act: -0.0000

Data Index: 1889146 (The Pile)

Max Activating Token Index: 885

Text #6

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2435. Min Act: -0.0000

Data Index: 1202322 (The Pile)

Max Activating Token Index: 899

Text #7

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2368. Min Act: -0.0000

Data Index: 150327 (The Pile)

Max Activating Token Index: 559

Text #8

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2414. Min Act: -0.0000

Data Index: 73172 (The Pile)

Max Activating Token Index: 1000

Text #9

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2330. Min Act: -0.0000

Data Index: 88601 (The Pile)

Max Activating Token Index: 886

Text #10

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2256. Min Act: -0.0000

Data Index: 1431169 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1350566 (The Pile)

Max Activating Token Index: 886

Text #12

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2138. Min Act: -0.0000

Data Index: 731156 (The Pile)

Max Activating Token Index: 807

Text #13

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2371. Min Act: -0.0000

Data Index: 1372811 (The Pile)

Max Activating Token Index: 805

Text #14

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2316. Min Act: -0.0000

Data Index: 484560 (The Pile)

Max Activating Token Index: 954

Text #15

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2287. Min Act: -0.0000

Data Index: 1041889 (The Pile)

Max Activating Token Index: 997

Text #16

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2228. Min Act: -0.0000

Data Index: 1251185 (The Pile)

Max Activating Token Index: 803

Text #17

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2258. Min Act: -0.0000

Data Index: 295220 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2142. Min Act: -0.0000

Data Index: 1470326 (The Pile)

Max Activating Token Index: 845

Text #19

Max Range: 0.3339. Min Range: -0.3339

Max Act: 0.2072. Min Act: -0.0000

Data Index: 1214790 (The Pile)

Max Activating Token Index: 917