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

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

Neuron 5560 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.7278. Min Act: -0.0000

Data Index: 336366 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5900. Min Act: -0.0000

Data Index: 745642 (C4 (Web Text))

Max Activating Token Index: 718

Text #2

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.6244. Min Act: -0.0000

Data Index: 1121037 (C4 (Web Text))

Max Activating Token Index: 278

Text #3

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5345. Min Act: -0.0000

Data Index: 1037431 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5174. Min Act: -0.0000

Data Index: 949049 (C4 (Web Text))

Max Activating Token Index: 128

Text #5

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5225. Min Act: -0.0000

Data Index: 1192147 (C4 (Web Text))

Max Activating Token Index: 289

Text #6

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5192. Min Act: -0.0000

Data Index: 1281319 (C4 (Web Text))

Max Activating Token Index: 353

Text #7

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5025. Min Act: -0.0000

Data Index: 1047667 (C4 (Web Text))

Max Activating Token Index: 261

Text #8

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5067. Min Act: -0.0000

Data Index: 47004 (C4 (Web Text))

Max Activating Token Index: 166

Text #9

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.5121. Min Act: -0.0000

Data Index: 873841 (C4 (Web Text))

Max Activating Token Index: 102

Text #10

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4687. Min Act: -0.0000

Data Index: 874765 (C4 (Web Text))

Max Activating Token Index: 313

Text #11

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4889. Min Act: -0.0000

Data Index: 1508439 (Python Code)

Max Activating Token Index: 646

Text #12

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4766. Min Act: -0.0000

Data Index: 1578274 (Python Code)

Max Activating Token Index: 191

Text #13

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4516. Min Act: -0.0000

Data Index: 846943 (C4 (Web Text))

Max Activating Token Index: 209

Text #14

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1401531 (Python Code)

Max Activating Token Index: 711

Text #15

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4506. Min Act: -0.0000

Data Index: 11841 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4348. Min Act: -0.0000

Data Index: 1377210 (Python Code)

Max Activating Token Index: 601

Text #17

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4229. Min Act: -0.0000

Data Index: 678682 (C4 (Web Text))

Max Activating Token Index: 251

Text #18

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4753. Min Act: -0.0000

Data Index: 151087 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 0.7278. Min Range: -0.7278

Max Act: 0.4548. Min Act: -0.0000

Data Index: 835487 (C4 (Web Text))

Max Activating Token Index: 157