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

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

Neuron 3797 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: 0.0440. Min Range: -0.0440

Max Act: 0.0440. Min Act: -0.0002

Data Index: 532953 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0404. Min Act: -0.0002

Data Index: 467807 (C4 (Web Text))

Max Activating Token Index: 398

Text #2

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0432. Min Act: -0.0002

Data Index: 6436 (C4 (Web Text))

Max Activating Token Index: 819

Text #3

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0411. Min Act: -0.0002

Data Index: 553702 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0425. Min Act: -0.0002

Data Index: 1019291 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0432. Min Act: -0.0002

Data Index: 1085195 (C4 (Web Text))

Max Activating Token Index: 899

Text #6

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0409. Min Act: -0.0002

Data Index: 826267 (C4 (Web Text))

Max Activating Token Index: 872

Text #7

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0382. Min Act: -0.0002

Data Index: 69361 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0399. Min Act: -0.0002

Data Index: 1083016 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0351. Min Act: -0.0002

Data Index: 1264195 (C4 (Web Text))

Max Activating Token Index: 555

Text #10

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0396. Min Act: -0.0002

Data Index: 832989 (C4 (Web Text))

Max Activating Token Index: 980

Text #11

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0360. Min Act: -0.0002

Data Index: 260488 (C4 (Web Text))

Max Activating Token Index: 706

Text #12

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0346. Min Act: -0.0002

Data Index: 184300 (C4 (Web Text))

Max Activating Token Index: 732

Text #13

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0334. Min Act: -0.0002

Data Index: 155393 (C4 (Web Text))

Max Activating Token Index: 860

Text #14

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0384. Min Act: -0.0002

Data Index: 295937 (C4 (Web Text))

Max Activating Token Index: 857

Text #15

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0370. Min Act: -0.0002

Data Index: 710378 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0375. Min Act: -0.0002

Data Index: 804702 (C4 (Web Text))

Max Activating Token Index: 60

Text #17

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0410. Min Act: -0.0002

Data Index: 608288 (C4 (Web Text))

Max Activating Token Index: 235

Text #18

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0370. Min Act: -0.0002

Data Index: 229127 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.0440. Min Range: -0.0440

Max Act: 0.0347. Min Act: -0.0002

Data Index: 420624 (C4 (Web Text))

Max Activating Token Index: 630