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

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

Neuron 4189 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0221. Min Act: -0.0000

Data Index: 254626 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0212. Min Act: -0.0000

Data Index: 103953 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0201. Min Act: -0.0000

Data Index: 647380 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0174. Min Act: -0.0000

Data Index: 551715 (C4 (Web Text))

Max Activating Token Index: 785

Text #4

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0173. Min Act: -0.0000

Data Index: 886431 (C4 (Web Text))

Max Activating Token Index: 556

Text #5

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0182. Min Act: -0.0000

Data Index: 913507 (C4 (Web Text))

Max Activating Token Index: 367

Text #6

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0164. Min Act: -0.0000

Data Index: 954062 (C4 (Web Text))

Max Activating Token Index: 510

Text #7

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0170. Min Act: -0.0000

Data Index: 450613 (C4 (Web Text))

Max Activating Token Index: 613

Text #8

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0167. Min Act: -0.0000

Data Index: 1060463 (C4 (Web Text))

Max Activating Token Index: 1009

Text #9

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0165. Min Act: -0.0000

Data Index: 789936 (C4 (Web Text))

Max Activating Token Index: 419

Text #10

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0168. Min Act: -0.0000

Data Index: 1570387 (Python Code)

Max Activating Token Index: 492

Text #11

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0155. Min Act: -0.0000

Data Index: 1111127 (C4 (Web Text))

Max Activating Token Index: 1000

Text #12

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0151. Min Act: -0.0000

Data Index: 16643 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0154. Min Act: -0.0000

Data Index: 1304320 (C4 (Web Text))

Max Activating Token Index: 817

Text #14

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0135. Min Act: -0.0000

Data Index: 620886 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0147. Min Act: -0.0000

Data Index: 1071159 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0150. Min Act: -0.0000

Data Index: 112778 (C4 (Web Text))

Max Activating Token Index: 863

Text #17

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0150. Min Act: -0.0000

Data Index: 1529122 (Python Code)

Max Activating Token Index: 699

Text #18

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0148. Min Act: -0.0000

Data Index: 160731 (C4 (Web Text))

Max Activating Token Index: 556

Text #19

Max Range: 0.0221. Min Range: -0.0221

Max Act: 0.0158. Min Act: -0.0000

Data Index: 1146006 (C4 (Web Text))

Max Activating Token Index: 387