Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 196 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2577. Min Act: -0.0001

Data Index: 841750 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2431. Min Act: -0.0001

Data Index: 154874 (C4 (Web Text))

Max Activating Token Index: 543

Text #2

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.3170. Min Act: -0.0001

Data Index: 98456 (C4 (Web Text))

Max Activating Token Index: 827

Text #3

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2216. Min Act: -0.0001

Data Index: 1222088 (C4 (Web Text))

Max Activating Token Index: 359

Text #4

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0985. Min Act: -0.0001

Data Index: 188332 (C4 (Web Text))

Max Activating Token Index: 408

Text #5

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1822. Min Act: -0.0001

Data Index: 753828 (C4 (Web Text))

Max Activating Token Index: 109

Text #6

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.3498. Min Act: -0.0001

Data Index: 603921 (C4 (Web Text))

Max Activating Token Index: 337

Text #7

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1878. Min Act: -0.0001

Data Index: 290547 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0021. Min Act: -0.0001

Data Index: 328464 (C4 (Web Text))

Max Activating Token Index: 161

Text #9

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1882. Min Act: -0.0001

Data Index: 37436 (C4 (Web Text))

Max Activating Token Index: 839

Text #10

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2606. Min Act: -0.0001

Data Index: 539495 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2081. Min Act: -0.0001

Data Index: 496937 (C4 (Web Text))

Max Activating Token Index: 61

Text #12

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1073. Min Act: -0.0001

Data Index: 18807 (C4 (Web Text))

Max Activating Token Index: 351

Text #13

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1142. Min Act: -0.0001

Data Index: 403074 (C4 (Web Text))

Max Activating Token Index: 245

Text #14

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0895. Min Act: -0.0002

Data Index: 154860 (C4 (Web Text))

Max Activating Token Index: 753

Text #15

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0512. Min Act: -0.0001

Data Index: 750522 (C4 (Web Text))

Max Activating Token Index: 932

Text #16

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1905. Min Act: -0.0001

Data Index: 1555494 (Python Code)

Max Activating Token Index: 141

Text #17

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.2145. Min Act: -0.0001

Data Index: 759966 (C4 (Web Text))

Max Activating Token Index: 114

Text #18

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.0269. Min Act: -0.0001

Data Index: 1223265 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 1.3498. Min Range: -1.3498

Max Act: 1.1372. Min Act: -0.0001

Data Index: 1339862 (C4 (Web Text))

Max Activating Token Index: 523