Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3696 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.9893. Min Act: -0.0001

Data Index: 1058132 (C4 (Web Text))

Max Activating Token Index: 308

Text #1

Max Range: 1.0445. Min Range: -1.0445

Max Act: 1.0445. Min Act: -0.0001

Data Index: 974073 (C4 (Web Text))

Max Activating Token Index: 351

Text #2

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8880. Min Act: -0.0001

Data Index: 475269 (C4 (Web Text))

Max Activating Token Index: 369

Text #3

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8802. Min Act: -0.0001

Data Index: 646008 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8643. Min Act: -0.0001

Data Index: 1165050 (C4 (Web Text))

Max Activating Token Index: 69

Text #5

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8020. Min Act: -0.0002

Data Index: 964147 (C4 (Web Text))

Max Activating Token Index: 922

Text #6

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7970. Min Act: -0.0002

Data Index: 447454 (C4 (Web Text))

Max Activating Token Index: 226

Text #7

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8348. Min Act: -0.0001

Data Index: 318421 (C4 (Web Text))

Max Activating Token Index: 392

Text #8

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7821. Min Act: -0.0001

Data Index: 1090836 (C4 (Web Text))

Max Activating Token Index: 119

Text #9

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7563. Min Act: -0.0001

Data Index: 1252952 (C4 (Web Text))

Max Activating Token Index: 146

Text #10

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7907. Min Act: -0.0001

Data Index: 106194 (C4 (Web Text))

Max Activating Token Index: 574

Text #11

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7386. Min Act: -0.0002

Data Index: 1013851 (C4 (Web Text))

Max Activating Token Index: 511

Text #12

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7435. Min Act: -0.0002

Data Index: 734420 (C4 (Web Text))

Max Activating Token Index: 56

Text #13

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.8155. Min Act: -0.0001

Data Index: 1184354 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7347. Min Act: -0.0001

Data Index: 211153 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7273. Min Act: -0.0001

Data Index: 1141916 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7218. Min Act: -0.0002

Data Index: 199274 (C4 (Web Text))

Max Activating Token Index: 107

Text #17

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7349. Min Act: -0.0001

Data Index: 766489 (C4 (Web Text))

Max Activating Token Index: 751

Text #18

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7207. Min Act: -0.0001

Data Index: 1221183 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 1.0445. Min Range: -1.0445

Max Act: 0.7203. Min Act: -0.0002

Data Index: 458552 (C4 (Web Text))

Max Activating Token Index: 690