Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4449 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.3323. Min Act: -0.0000

Data Index: 65538 (C4 (Web Text))

Max Activating Token Index: 643

Text #1

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2467. Min Act: -0.0000

Data Index: 560928 (C4 (Web Text))

Max Activating Token Index: 83

Text #2

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2693. Min Act: -0.0000

Data Index: 781415 (C4 (Web Text))

Max Activating Token Index: 785

Text #3

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2355. Min Act: -0.0000

Data Index: 851695 (C4 (Web Text))

Max Activating Token Index: 768

Text #4

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2517. Min Act: -0.0000

Data Index: 82909 (C4 (Web Text))

Max Activating Token Index: 173

Text #5

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2212. Min Act: -0.0000

Data Index: 335976 (C4 (Web Text))

Max Activating Token Index: 36

Text #6

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2144. Min Act: -0.0000

Data Index: 1021044 (C4 (Web Text))

Max Activating Token Index: 589

Text #7

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2205. Min Act: -0.0000

Data Index: 764178 (C4 (Web Text))

Max Activating Token Index: 506

Text #8

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2179. Min Act: -0.0000

Data Index: 16389 (C4 (Web Text))

Max Activating Token Index: 967

Text #9

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2166. Min Act: -0.0000

Data Index: 947061 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1160245 (C4 (Web Text))

Max Activating Token Index: 374

Text #11

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2144. Min Act: -0.0000

Data Index: 939921 (C4 (Web Text))

Max Activating Token Index: 361

Text #12

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2303. Min Act: -0.0000

Data Index: 995834 (C4 (Web Text))

Max Activating Token Index: 258

Text #13

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2139. Min Act: -0.0000

Data Index: 1099064 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2114. Min Act: -0.0000

Data Index: 1130509 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2173. Min Act: -0.0000

Data Index: 1359541 (C4 (Web Text))

Max Activating Token Index: 716

Text #16

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2073. Min Act: -0.0000

Data Index: 539196 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.2007. Min Act: -0.0000

Data Index: 765580 (C4 (Web Text))

Max Activating Token Index: 165

Text #18

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.1948. Min Act: -0.0000

Data Index: 491183 (C4 (Web Text))

Max Activating Token Index: 438

Text #19

Max Range: 0.3323. Min Range: -0.3323

Max Act: 0.1928. Min Act: -0.0000

Data Index: 223410 (C4 (Web Text))

Max Activating Token Index: 356