Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4899 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3947. Min Act: -0.0000

Data Index: 1251468 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3509. Min Act: -0.0000

Data Index: 453766 (C4 (Web Text))

Max Activating Token Index: 211

Text #2

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3576. Min Act: -0.0000

Data Index: 1274758 (C4 (Web Text))

Max Activating Token Index: 489

Text #3

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3429. Min Act: -0.0000

Data Index: 278564 (C4 (Web Text))

Max Activating Token Index: 819

Text #4

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3447. Min Act: -0.0000

Data Index: 439942 (C4 (Web Text))

Max Activating Token Index: 411

Text #5

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3224. Min Act: -0.0000

Data Index: 1193091 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3438. Min Act: -0.0000

Data Index: 812052 (C4 (Web Text))

Max Activating Token Index: 583

Text #7

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3225. Min Act: -0.0000

Data Index: 550329 (C4 (Web Text))

Max Activating Token Index: 367

Text #8

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3309. Min Act: -0.0000

Data Index: 1280418 (C4 (Web Text))

Max Activating Token Index: 769

Text #9

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3386. Min Act: -0.0000

Data Index: 1067717 (C4 (Web Text))

Max Activating Token Index: 983

Text #10

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3185. Min Act: -0.0000

Data Index: 1333591 (C4 (Web Text))

Max Activating Token Index: 975

Text #11

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3269. Min Act: -0.0000

Data Index: 588575 (C4 (Web Text))

Max Activating Token Index: 461

Text #12

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3161. Min Act: -0.0000

Data Index: 760099 (C4 (Web Text))

Max Activating Token Index: 983

Text #13

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3198. Min Act: -0.0000

Data Index: 411697 (C4 (Web Text))

Max Activating Token Index: 411

Text #14

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.2902. Min Act: -0.0000

Data Index: 22845 (C4 (Web Text))

Max Activating Token Index: 751

Text #15

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.2988. Min Act: -0.0000

Data Index: 538213 (C4 (Web Text))

Max Activating Token Index: 426

Text #16

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.2958. Min Act: -0.0000

Data Index: 280661 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.2928. Min Act: -0.0000

Data Index: 1322305 (C4 (Web Text))

Max Activating Token Index: 713

Text #18

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.2944. Min Act: -0.0000

Data Index: 1193966 (C4 (Web Text))

Max Activating Token Index: 393

Text #19

Max Range: 0.3947. Min Range: -0.3947

Max Act: 0.3114. Min Act: -0.0000

Data Index: 1328041 (C4 (Web Text))

Max Activating Token Index: 216