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

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

Neuron 4333 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: 0.4163. Min Range: -0.4163

Max Act: 0.4163. Min Act: -0.0000

Data Index: 485154 (C4 (Web Text))

Max Activating Token Index: 609

Text #1

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3991. Min Act: -0.0000

Data Index: 256281 (C4 (Web Text))

Max Activating Token Index: 217

Text #2

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3441. Min Act: -0.0000

Data Index: 8239 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3215. Min Act: -0.0000

Data Index: 870739 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3023. Min Act: -0.0000

Data Index: 605887 (C4 (Web Text))

Max Activating Token Index: 716

Text #5

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3102. Min Act: -0.0000

Data Index: 503313 (C4 (Web Text))

Max Activating Token Index: 343

Text #6

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1346810 (C4 (Web Text))

Max Activating Token Index: 327

Text #7

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2597. Min Act: -0.0000

Data Index: 437859 (C4 (Web Text))

Max Activating Token Index: 198

Text #8

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2941. Min Act: -0.0000

Data Index: 778922 (C4 (Web Text))

Max Activating Token Index: 649

Text #9

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1131126 (C4 (Web Text))

Max Activating Token Index: 791

Text #10

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2482. Min Act: -0.0000

Data Index: 748608 (C4 (Web Text))

Max Activating Token Index: 620

Text #11

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3105. Min Act: -0.0000

Data Index: 848576 (C4 (Web Text))

Max Activating Token Index: 902

Text #12

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2465. Min Act: -0.0000

Data Index: 363468 (C4 (Web Text))

Max Activating Token Index: 229

Text #13

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2774. Min Act: -0.0000

Data Index: 1407021 (Python Code)

Max Activating Token Index: 235

Text #14

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2556. Min Act: -0.0000

Data Index: 292050 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2643. Min Act: -0.0000

Data Index: 685837 (C4 (Web Text))

Max Activating Token Index: 676

Text #16

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2730. Min Act: -0.0000

Data Index: 473629 (C4 (Web Text))

Max Activating Token Index: 743

Text #17

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.3179. Min Act: -0.0000

Data Index: 1133579 (C4 (Web Text))

Max Activating Token Index: 152

Text #18

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2716. Min Act: -0.0000

Data Index: 272963 (C4 (Web Text))

Max Activating Token Index: 73

Text #19

Max Range: 0.4163. Min Range: -0.4163

Max Act: 0.2673. Min Act: -0.0000

Data Index: 125702 (C4 (Web Text))

Max Activating Token Index: 352