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

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

Neuron 541 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.7658. Min Act: -0.0000

Data Index: 568407 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.5556. Min Act: -0.0000

Data Index: 257098 (C4 (Web Text))

Max Activating Token Index: 144

Text #2

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.6346. Min Act: -0.0000

Data Index: 660909 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4098. Min Act: -0.0000

Data Index: 636802 (C4 (Web Text))

Max Activating Token Index: 200

Text #4

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.3831. Min Act: -0.0000

Data Index: 351969 (C4 (Web Text))

Max Activating Token Index: 109

Text #5

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.2149. Min Act: -0.0000

Data Index: 1062599 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.3564. Min Act: -0.0000

Data Index: 809054 (C4 (Web Text))

Max Activating Token Index: 123

Text #7

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.3189. Min Act: -0.0000

Data Index: 857434 (C4 (Web Text))

Max Activating Token Index: 195

Text #8

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.1369. Min Act: -0.0000

Data Index: 846226 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.2216. Min Act: -0.0000

Data Index: 1246761 (C4 (Web Text))

Max Activating Token Index: 184

Text #10

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.2154. Min Act: -0.0000

Data Index: 1148993 (C4 (Web Text))

Max Activating Token Index: 168

Text #11

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.4993. Min Act: -0.0000

Data Index: 1284045 (C4 (Web Text))

Max Activating Token Index: 940

Text #12

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.2934. Min Act: -0.0000

Data Index: 1008330 (C4 (Web Text))

Max Activating Token Index: 167

Text #13

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.0292. Min Act: -0.0000

Data Index: 205208 (C4 (Web Text))

Max Activating Token Index: 140

Text #14

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.2041. Min Act: -0.0000

Data Index: 873984 (C4 (Web Text))

Max Activating Token Index: 136

Text #15

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.1837. Min Act: -0.0000

Data Index: 307925 (C4 (Web Text))

Max Activating Token Index: 962

Text #16

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.0262. Min Act: -0.0000

Data Index: 1066986 (C4 (Web Text))

Max Activating Token Index: 954

Text #17

Max Range: 3.7658. Min Range: -3.7658

Max Act: 3.1755. Min Act: -0.0000

Data Index: 453189 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 3.7658. Min Range: -3.7658

Max Act: 2.9400. Min Act: -0.0000

Data Index: 452072 (C4 (Web Text))

Max Activating Token Index: 402

Text #19

Max Range: 3.7658. Min Range: -3.7658

Max Act: 2.9869. Min Act: -0.0000

Data Index: 1084290 (C4 (Web Text))

Max Activating Token Index: 190