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

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

Neuron 4233 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1283597 (C4 (Web Text))

Max Activating Token Index: 24

Text #1

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0169. Min Act: -0.0002

Data Index: 341093 (C4 (Web Text))

Max Activating Token Index: 165

Text #2

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0002

Data Index: 642576 (C4 (Web Text))

Max Activating Token Index: 127

Text #3

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0168. Min Act: -0.0002

Data Index: 569067 (C4 (Web Text))

Max Activating Token Index: 81

Text #4

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0171. Min Act: -0.0002

Data Index: 399875 (C4 (Web Text))

Max Activating Token Index: 149

Text #5

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0167. Min Act: -0.0002

Data Index: 815029 (C4 (Web Text))

Max Activating Token Index: 301

Text #6

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1096663 (C4 (Web Text))

Max Activating Token Index: 966

Text #7

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0162. Min Act: -0.0002

Data Index: 554397 (C4 (Web Text))

Max Activating Token Index: 87

Text #8

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0161. Min Act: -0.0002

Data Index: 86298 (C4 (Web Text))

Max Activating Token Index: 420

Text #9

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0161. Min Act: -0.0002

Data Index: 475995 (C4 (Web Text))

Max Activating Token Index: 105

Text #10

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1302892 (C4 (Web Text))

Max Activating Token Index: 70

Text #11

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0160. Min Act: -0.0002

Data Index: 752443 (C4 (Web Text))

Max Activating Token Index: 717

Text #12

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0160. Min Act: -0.0002

Data Index: 878512 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0159. Min Act: -0.0002

Data Index: 908107 (C4 (Web Text))

Max Activating Token Index: 853

Text #14

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0159. Min Act: -0.0002

Data Index: 373368 (C4 (Web Text))

Max Activating Token Index: 291

Text #15

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0162. Min Act: -0.0002

Data Index: 713286 (C4 (Web Text))

Max Activating Token Index: 119

Text #16

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0158. Min Act: -0.0002

Data Index: 1326879 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0154. Min Act: -0.0002

Data Index: 1059183 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0157. Min Act: -0.0002

Data Index: 995517 (C4 (Web Text))

Max Activating Token Index: 370

Text #19

Max Range: 0.0175. Min Range: -0.0175

Max Act: 0.0157. Min Act: -0.0002

Data Index: 515856 (C4 (Web Text))

Max Activating Token Index: 72