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

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

Neuron 4747 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.4178. Min Act: -0.0000

Data Index: 131053 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2887. Min Act: -0.0000

Data Index: 370758 (C4 (Web Text))

Max Activating Token Index: 205

Text #2

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2150. Min Act: -0.0000

Data Index: 500299 (C4 (Web Text))

Max Activating Token Index: 179

Text #3

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.2398. Min Act: -0.0000

Data Index: 441393 (C4 (Web Text))

Max Activating Token Index: 518

Text #4

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.3166. Min Act: -0.0000

Data Index: 1025271 (C4 (Web Text))

Max Activating Token Index: 1021

Text #5

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0859. Min Act: -0.0000

Data Index: 1208368 (C4 (Web Text))

Max Activating Token Index: 777

Text #6

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9954. Min Act: -0.0000

Data Index: 985624 (C4 (Web Text))

Max Activating Token Index: 74

Text #7

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0137. Min Act: -0.0000

Data Index: 1329819 (C4 (Web Text))

Max Activating Token Index: 153

Text #8

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9588. Min Act: -0.0000

Data Index: 1299369 (C4 (Web Text))

Max Activating Token Index: 15

Text #9

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0187. Min Act: -0.0000

Data Index: 761904 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0241. Min Act: -0.0000

Data Index: 1041133 (C4 (Web Text))

Max Activating Token Index: 789

Text #11

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0139. Min Act: -0.0000

Data Index: 984160 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0019. Min Act: -0.0000

Data Index: 184638 (C4 (Web Text))

Max Activating Token Index: 411

Text #13

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9919. Min Act: -0.0000

Data Index: 808186 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9901. Min Act: -0.0000

Data Index: 980758 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 1.4178. Min Range: -1.4178

Max Act: 1.0336. Min Act: -0.0000

Data Index: 739853 (C4 (Web Text))

Max Activating Token Index: 778

Text #16

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.7629. Min Act: -0.0000

Data Index: 556880 (C4 (Web Text))

Max Activating Token Index: 675

Text #17

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9759. Min Act: -0.0000

Data Index: 703857 (C4 (Web Text))

Max Activating Token Index: 253

Text #18

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1146796 (C4 (Web Text))

Max Activating Token Index: 61

Text #19

Max Range: 1.4178. Min Range: -1.4178

Max Act: 0.9043. Min Act: -0.0000

Data Index: 136897 (C4 (Web Text))

Max Activating Token Index: 260