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

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

Neuron 2209 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.9164. Min Act: -0.0002

Data Index: 272739 (C4 (Web Text))

Max Activating Token Index: 661

Text #1

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.8495. Min Act: -0.0002

Data Index: 553738 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.7794. Min Act: -0.0002

Data Index: 722649 (C4 (Web Text))

Max Activating Token Index: 680

Text #3

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.7113. Min Act: -0.0002

Data Index: 943504 (C4 (Web Text))

Max Activating Token Index: 91

Text #4

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.7113. Min Act: -0.0002

Data Index: 367670 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.7227. Min Act: -0.0002

Data Index: 797882 (C4 (Web Text))

Max Activating Token Index: 834

Text #6

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.7029. Min Act: -0.0002

Data Index: 309100 (C4 (Web Text))

Max Activating Token Index: 97

Text #7

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6913. Min Act: -0.0002

Data Index: 505982 (C4 (Web Text))

Max Activating Token Index: 64

Text #8

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6819. Min Act: -0.0002

Data Index: 852033 (C4 (Web Text))

Max Activating Token Index: 74

Text #9

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6745. Min Act: -0.0002

Data Index: 169362 (C4 (Web Text))

Max Activating Token Index: 83

Text #10

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6742. Min Act: -0.0002

Data Index: 336873 (C4 (Web Text))

Max Activating Token Index: 47

Text #11

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6408. Min Act: -0.0002

Data Index: 870471 (C4 (Web Text))

Max Activating Token Index: 147

Text #12

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6427. Min Act: -0.0002

Data Index: 261915 (C4 (Web Text))

Max Activating Token Index: 342

Text #13

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6058. Min Act: -0.0002

Data Index: 183989 (C4 (Web Text))

Max Activating Token Index: 23

Text #14

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.5999. Min Act: -0.0002

Data Index: 235448 (C4 (Web Text))

Max Activating Token Index: 469

Text #15

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6397. Min Act: -0.0002

Data Index: 888087 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.5594. Min Act: -0.0002

Data Index: 1081998 (C4 (Web Text))

Max Activating Token Index: 336

Text #17

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6155. Min Act: -0.0002

Data Index: 736642 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.5941. Min Act: -0.0002

Data Index: 1313457 (C4 (Web Text))

Max Activating Token Index: 315

Text #19

Max Range: 0.9164. Min Range: -0.9164

Max Act: 0.6338. Min Act: -0.0002

Data Index: 278342 (C4 (Web Text))

Max Activating Token Index: 808