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

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

Neuron 3451 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.7234. Min Act: -0.0000

Data Index: 432531 (C4 (Web Text))

Max Activating Token Index: 870

Text #1

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6254. Min Act: -0.0000

Data Index: 1187918 (C4 (Web Text))

Max Activating Token Index: 667

Text #2

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5844. Min Act: -0.0000

Data Index: 140024 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.6151. Min Act: -0.0000

Data Index: 853450 (C4 (Web Text))

Max Activating Token Index: 631

Text #4

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5535. Min Act: -0.0000

Data Index: 341811 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5920. Min Act: -0.0000

Data Index: 809170 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5653. Min Act: -0.0000

Data Index: 1064285 (C4 (Web Text))

Max Activating Token Index: 563

Text #7

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5363. Min Act: -0.0000

Data Index: 687873 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5688. Min Act: -0.0000

Data Index: 1092569 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5469. Min Act: -0.0000

Data Index: 90762 (C4 (Web Text))

Max Activating Token Index: 475

Text #10

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.4979. Min Act: -0.0000

Data Index: 1077568 (C4 (Web Text))

Max Activating Token Index: 356

Text #11

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5251. Min Act: -0.0000

Data Index: 945 (C4 (Web Text))

Max Activating Token Index: 148

Text #12

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5240. Min Act: -0.0000

Data Index: 228028 (C4 (Web Text))

Max Activating Token Index: 691

Text #13

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5572. Min Act: -0.0000

Data Index: 879424 (C4 (Web Text))

Max Activating Token Index: 394

Text #14

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5053. Min Act: -0.0000

Data Index: 68268 (C4 (Web Text))

Max Activating Token Index: 263

Text #15

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5275. Min Act: -0.0000

Data Index: 502860 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5275. Min Act: -0.0000

Data Index: 602339 (C4 (Web Text))

Max Activating Token Index: 669

Text #17

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5249. Min Act: -0.0000

Data Index: 662616 (C4 (Web Text))

Max Activating Token Index: 526

Text #18

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1289446 (C4 (Web Text))

Max Activating Token Index: 520

Text #19

Max Range: 0.7234. Min Range: -0.7234

Max Act: 0.5047. Min Act: -0.0000

Data Index: 1327031 (C4 (Web Text))

Max Activating Token Index: 741