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

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

Neuron 4763 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1402. Min Act: -0.0000

Data Index: 1357442 (C4 (Web Text))

Max Activating Token Index: 20

Text #1

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1267. Min Act: -0.0000

Data Index: 1507554 (Python Code)

Max Activating Token Index: 108

Text #2

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1215. Min Act: -0.0000

Data Index: 14758 (C4 (Web Text))

Max Activating Token Index: 400

Text #3

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1293. Min Act: -0.0000

Data Index: 636740 (C4 (Web Text))

Max Activating Token Index: 424

Text #4

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1254. Min Act: -0.0000

Data Index: 64842 (C4 (Web Text))

Max Activating Token Index: 790

Text #5

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1213. Min Act: -0.0000

Data Index: 198068 (C4 (Web Text))

Max Activating Token Index: 910

Text #6

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1161. Min Act: -0.0000

Data Index: 568506 (C4 (Web Text))

Max Activating Token Index: 40

Text #7

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1121. Min Act: -0.0000

Data Index: 677077 (C4 (Web Text))

Max Activating Token Index: 734

Text #8

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1083. Min Act: -0.0000

Data Index: 918558 (C4 (Web Text))

Max Activating Token Index: 208

Text #9

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1092. Min Act: -0.0000

Data Index: 1141981 (C4 (Web Text))

Max Activating Token Index: 69

Text #10

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1089. Min Act: -0.0000

Data Index: 1464330 (Python Code)

Max Activating Token Index: 115

Text #11

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1123. Min Act: -0.0000

Data Index: 123449 (C4 (Web Text))

Max Activating Token Index: 917

Text #12

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1045. Min Act: -0.0000

Data Index: 206225 (C4 (Web Text))

Max Activating Token Index: 45

Text #13

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1073. Min Act: -0.0000

Data Index: 211246 (C4 (Web Text))

Max Activating Token Index: 473

Text #14

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1059. Min Act: -0.0000

Data Index: 269029 (C4 (Web Text))

Max Activating Token Index: 645

Text #15

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1062. Min Act: -0.0000

Data Index: 1079009 (C4 (Web Text))

Max Activating Token Index: 861

Text #16

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1035. Min Act: -0.0000

Data Index: 472219 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1026. Min Act: -0.0000

Data Index: 653940 (C4 (Web Text))

Max Activating Token Index: 959

Text #18

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1017. Min Act: -0.0000

Data Index: 972150 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.1402. Min Range: -0.1402

Max Act: 0.1046. Min Act: -0.0000

Data Index: 561699 (C4 (Web Text))

Max Activating Token Index: 107