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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 884 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0414. Min Act: -0.0002

Data Index: 612117 (C4 (Web Text))

Max Activating Token Index: 882

Text #1

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1585691 (Python Code)

Max Activating Token Index: 861

Text #2

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1218902 (C4 (Web Text))

Max Activating Token Index: 451

Text #3

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0365. Min Act: -0.0002

Data Index: 487909 (C4 (Web Text))

Max Activating Token Index: 57

Text #4

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1240706 (C4 (Web Text))

Max Activating Token Index: 66

Text #5

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0351. Min Act: -0.0002

Data Index: 987335 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0316. Min Act: -0.0002

Data Index: 786263 (C4 (Web Text))

Max Activating Token Index: 954

Text #7

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0307. Min Act: -0.0002

Data Index: 1033099 (C4 (Web Text))

Max Activating Token Index: 158

Text #8

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0296. Min Act: -0.0002

Data Index: 864577 (C4 (Web Text))

Max Activating Token Index: 441

Text #9

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1427752 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0290. Min Act: -0.0002

Data Index: 768451 (C4 (Web Text))

Max Activating Token Index: 134

Text #11

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1398744 (Python Code)

Max Activating Token Index: 900

Text #12

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0304. Min Act: -0.0002

Data Index: 1172809 (C4 (Web Text))

Max Activating Token Index: 745

Text #13

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0270. Min Act: -0.0002

Data Index: 815050 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0268. Min Act: -0.0002

Data Index: 976390 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0277. Min Act: -0.0002

Data Index: 782014 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0275. Min Act: -0.0002

Data Index: 657312 (C4 (Web Text))

Max Activating Token Index: 90

Text #17

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1414263 (Python Code)

Max Activating Token Index: 821

Text #18

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1134102 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0414. Min Range: -0.0414

Max Act: 0.0224. Min Act: -0.0002

Data Index: 1044123 (C4 (Web Text))

Max Activating Token Index: 657