Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1780 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0360. Min Act: -0.0004

Data Index: 936885 (C4 (Web Text))

Max Activating Token Index: 940

Text #1

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0346. Min Act: -0.0003

Data Index: 774771 (C4 (Web Text))

Max Activating Token Index: 579

Text #2

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0335. Min Act: -0.0003

Data Index: 606995 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0331. Min Act: -0.0004

Data Index: 224565 (C4 (Web Text))

Max Activating Token Index: 245

Text #4

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0326. Min Act: -0.0003

Data Index: 1344834 (C4 (Web Text))

Max Activating Token Index: 998

Text #5

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0314. Min Act: -0.0003

Data Index: 951191 (C4 (Web Text))

Max Activating Token Index: 634

Text #6

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0312. Min Act: -0.0003

Data Index: 286742 (C4 (Web Text))

Max Activating Token Index: 397

Text #7

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0316. Min Act: -0.0003

Data Index: 978658 (C4 (Web Text))

Max Activating Token Index: 521

Text #8

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0316. Min Act: -0.0003

Data Index: 1320816 (C4 (Web Text))

Max Activating Token Index: 662

Text #9

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0310. Min Act: -0.0003

Data Index: 53519 (C4 (Web Text))

Max Activating Token Index: 850

Text #10

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0298. Min Act: -0.0003

Data Index: 947977 (C4 (Web Text))

Max Activating Token Index: 890

Text #11

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0313. Min Act: -0.0004

Data Index: 1169656 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0311. Min Act: -0.0003

Data Index: 605004 (C4 (Web Text))

Max Activating Token Index: 970

Text #13

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0293. Min Act: -0.0003

Data Index: 1287521 (C4 (Web Text))

Max Activating Token Index: 70

Text #14

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0302. Min Act: -0.0003

Data Index: 277375 (C4 (Web Text))

Max Activating Token Index: 47

Text #15

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0292. Min Act: -0.0003

Data Index: 772085 (C4 (Web Text))

Max Activating Token Index: 513

Text #16

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1258070 (C4 (Web Text))

Max Activating Token Index: 173

Text #17

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0294. Min Act: -0.0004

Data Index: 962419 (C4 (Web Text))

Max Activating Token Index: 1008

Text #18

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0278. Min Act: -0.0004

Data Index: 986802 (C4 (Web Text))

Max Activating Token Index: 233

Text #19

Max Range: 0.0360. Min Range: -0.0360

Max Act: 0.0286. Min Act: -0.0003

Data Index: 252259 (C4 (Web Text))

Max Activating Token Index: 600