Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 766 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1383. Min Act: -0.0002

Data Index: 452951 (C4 (Web Text))

Max Activating Token Index: 827

Text #1

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1288. Min Act: -0.0002

Data Index: 1291690 (C4 (Web Text))

Max Activating Token Index: 346

Text #2

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1179. Min Act: -0.0002

Data Index: 1328136 (C4 (Web Text))

Max Activating Token Index: 979

Text #3

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1180. Min Act: -0.0002

Data Index: 1114421 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1145. Min Act: -0.0002

Data Index: 680276 (C4 (Web Text))

Max Activating Token Index: 221

Text #5

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1055. Min Act: -0.0002

Data Index: 889696 (C4 (Web Text))

Max Activating Token Index: 588

Text #6

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1153. Min Act: -0.0002

Data Index: 796774 (C4 (Web Text))

Max Activating Token Index: 420

Text #7

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1169. Min Act: -0.0002

Data Index: 968840 (C4 (Web Text))

Max Activating Token Index: 528

Text #8

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1094. Min Act: -0.0002

Data Index: 144710 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1094. Min Act: -0.0002

Data Index: 624998 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1092. Min Act: -0.0002

Data Index: 628516 (C4 (Web Text))

Max Activating Token Index: 673

Text #11

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1088. Min Act: -0.0002

Data Index: 454787 (C4 (Web Text))

Max Activating Token Index: 328

Text #12

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1084. Min Act: -0.0002

Data Index: 170629 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1043. Min Act: -0.0002

Data Index: 239526 (C4 (Web Text))

Max Activating Token Index: 155

Text #14

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1056. Min Act: -0.0002

Data Index: 1174267 (C4 (Web Text))

Max Activating Token Index: 185

Text #15

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1049. Min Act: -0.0002

Data Index: 967227 (C4 (Web Text))

Max Activating Token Index: 70

Text #16

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1037. Min Act: -0.0002

Data Index: 297033 (C4 (Web Text))

Max Activating Token Index: 378

Text #17

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1037. Min Act: -0.0002

Data Index: 415279 (C4 (Web Text))

Max Activating Token Index: 529

Text #18

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1089. Min Act: -0.0002

Data Index: 1109112 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 0.1383. Min Range: -0.1383

Max Act: 0.1015. Min Act: -0.0002

Data Index: 981591 (C4 (Web Text))

Max Activating Token Index: 807