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

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

Neuron 1596 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1310542 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0251. Min Act: -0.0006

Data Index: 33649 (C4 (Web Text))

Max Activating Token Index: 129

Text #2

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0242. Min Act: -0.0006

Data Index: 1001492 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0239. Min Act: -0.0006

Data Index: 1117366 (C4 (Web Text))

Max Activating Token Index: 624

Text #4

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0236. Min Act: -0.0006

Data Index: 859394 (C4 (Web Text))

Max Activating Token Index: 444

Text #5

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0230. Min Act: -0.0006

Data Index: 1104664 (C4 (Web Text))

Max Activating Token Index: 425

Text #6

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0229. Min Act: -0.0006

Data Index: 1305157 (C4 (Web Text))

Max Activating Token Index: 279

Text #7

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0235. Min Act: -0.0006

Data Index: 1126755 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0229. Min Act: -0.0006

Data Index: 244789 (C4 (Web Text))

Max Activating Token Index: 442

Text #9

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0227. Min Act: -0.0006

Data Index: 487633 (C4 (Web Text))

Max Activating Token Index: 535

Text #10

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0229. Min Act: -0.0006

Data Index: 866560 (C4 (Web Text))

Max Activating Token Index: 612

Text #11

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0227. Min Act: -0.0006

Data Index: 881619 (C4 (Web Text))

Max Activating Token Index: 365

Text #12

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0221. Min Act: -0.0006

Data Index: 1008485 (C4 (Web Text))

Max Activating Token Index: 210

Text #13

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0221. Min Act: -0.0006

Data Index: 367741 (C4 (Web Text))

Max Activating Token Index: 201

Text #14

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0210. Min Act: -0.0006

Data Index: 595249 (C4 (Web Text))

Max Activating Token Index: 948

Text #15

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0215. Min Act: -0.0006

Data Index: 827171 (C4 (Web Text))

Max Activating Token Index: 178

Text #16

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0215. Min Act: -0.0006

Data Index: 330734 (C4 (Web Text))

Max Activating Token Index: 560

Text #17

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0219. Min Act: -0.0006

Data Index: 995377 (C4 (Web Text))

Max Activating Token Index: 912

Text #18

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0214. Min Act: -0.0006

Data Index: 753570 (C4 (Web Text))

Max Activating Token Index: 883

Text #19

Max Range: 0.0287. Min Range: -0.0287

Max Act: 0.0212. Min Act: -0.0006

Data Index: 792723 (C4 (Web Text))

Max Activating Token Index: 109