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

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

Neuron 5065 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: 1.7201. Min Range: -1.7201

Max Act: 1.7201. Min Act: -0.0001

Data Index: 865342 (C4 (Web Text))

Max Activating Token Index: 848

Text #1

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.6260. Min Act: -0.0001

Data Index: 642 (C4 (Web Text))

Max Activating Token Index: 1016

Text #2

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.5310. Min Act: -0.0001

Data Index: 1071136 (C4 (Web Text))

Max Activating Token Index: 26

Text #3

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3471. Min Act: -0.0001

Data Index: 1353895 (C4 (Web Text))

Max Activating Token Index: 977

Text #4

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2254. Min Act: -0.0001

Data Index: 746749 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3958. Min Act: -0.0001

Data Index: 840245 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3255. Min Act: -0.0001

Data Index: 1241873 (C4 (Web Text))

Max Activating Token Index: 486

Text #7

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2980. Min Act: -0.0001

Data Index: 362549 (C4 (Web Text))

Max Activating Token Index: 52

Text #8

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3115. Min Act: -0.0001

Data Index: 818841 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3033. Min Act: -0.0001

Data Index: 985343 (C4 (Web Text))

Max Activating Token Index: 11

Text #10

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3336. Min Act: -0.0001

Data Index: 734414 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.3318. Min Act: -0.0001

Data Index: 1003817 (C4 (Web Text))

Max Activating Token Index: 106

Text #12

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2932. Min Act: -0.0001

Data Index: 1313748 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2808. Min Act: -0.0001

Data Index: 883691 (C4 (Web Text))

Max Activating Token Index: 834

Text #14

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2160. Min Act: -0.0001

Data Index: 21300 (C4 (Web Text))

Max Activating Token Index: 5

Text #15

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2924. Min Act: -0.0001

Data Index: 817020 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.0379. Min Act: -0.0001

Data Index: 469250 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.1711. Min Act: -0.0001

Data Index: 1338410 (C4 (Web Text))

Max Activating Token Index: 486

Text #18

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.2708. Min Act: -0.0001

Data Index: 1158157 (C4 (Web Text))

Max Activating Token Index: 213

Text #19

Max Range: 1.7201. Min Range: -1.7201

Max Act: 1.1584. Min Act: -0.0001

Data Index: 1310064 (C4 (Web Text))

Max Activating Token Index: 921