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

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

Neuron 3988 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0382. Min Act: -0.0003

Data Index: 1342830 (C4 (Web Text))

Max Activating Token Index: 566

Text #1

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0333. Min Act: -0.0003

Data Index: 42996 (C4 (Web Text))

Max Activating Token Index: 154

Text #2

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0338. Min Act: -0.0003

Data Index: 481430 (C4 (Web Text))

Max Activating Token Index: 517

Text #3

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0324. Min Act: -0.0003

Data Index: 314756 (C4 (Web Text))

Max Activating Token Index: 182

Text #4

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0323. Min Act: -0.0003

Data Index: 1038344 (C4 (Web Text))

Max Activating Token Index: 340

Text #5

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1146712 (C4 (Web Text))

Max Activating Token Index: 949

Text #6

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0325. Min Act: -0.0003

Data Index: 531902 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0242. Min Act: -0.0003

Data Index: 492923 (C4 (Web Text))

Max Activating Token Index: 546

Text #8

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1562801 (Python Code)

Max Activating Token Index: 906

Text #9

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0294. Min Act: -0.0003

Data Index: 1040551 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0270. Min Act: -0.0003

Data Index: 377478 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0278. Min Act: -0.0003

Data Index: 862206 (C4 (Web Text))

Max Activating Token Index: 883

Text #12

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0270. Min Act: -0.0003

Data Index: 983279 (C4 (Web Text))

Max Activating Token Index: 532

Text #13

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0242. Min Act: -0.0003

Data Index: 17910 (C4 (Web Text))

Max Activating Token Index: 970

Text #14

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0236. Min Act: -0.0003

Data Index: 468466 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0281. Min Act: -0.0003

Data Index: 1604221 (Python Code)

Max Activating Token Index: 147

Text #16

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0251. Min Act: -0.0003

Data Index: 671923 (C4 (Web Text))

Max Activating Token Index: 365

Text #17

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1095156 (C4 (Web Text))

Max Activating Token Index: 618

Text #18

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0278. Min Act: -0.0003

Data Index: 1624221 (Python Code)

Max Activating Token Index: 724

Text #19

Max Range: 0.0382. Min Range: -0.0382

Max Act: 0.0236. Min Act: -0.0003

Data Index: 1053634 (C4 (Web Text))

Max Activating Token Index: 420