Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2608 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3197. Min Act: -0.0001

Data Index: 1034386 (C4 (Web Text))

Max Activating Token Index: 758

Text #1

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3124. Min Act: -0.0001

Data Index: 1215542 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2941. Min Act: -0.0001

Data Index: 327354 (C4 (Web Text))

Max Activating Token Index: 745

Text #3

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3095. Min Act: -0.0001

Data Index: 46962 (C4 (Web Text))

Max Activating Token Index: 994

Text #4

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3103. Min Act: -0.0001

Data Index: 1022032 (C4 (Web Text))

Max Activating Token Index: 931

Text #5

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.3031. Min Act: -0.0001

Data Index: 294117 (C4 (Web Text))

Max Activating Token Index: 389

Text #6

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2890. Min Act: -0.0001

Data Index: 1100024 (C4 (Web Text))

Max Activating Token Index: 170

Text #7

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2968. Min Act: -0.0001

Data Index: 1334229 (C4 (Web Text))

Max Activating Token Index: 842

Text #8

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2766. Min Act: -0.0001

Data Index: 665823 (C4 (Web Text))

Max Activating Token Index: 417

Text #9

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2796. Min Act: -0.0001

Data Index: 419381 (C4 (Web Text))

Max Activating Token Index: 237

Text #10

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2941. Min Act: -0.0001

Data Index: 350034 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2781. Min Act: -0.0001

Data Index: 627720 (C4 (Web Text))

Max Activating Token Index: 723

Text #12

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2804. Min Act: -0.0001

Data Index: 341714 (C4 (Web Text))

Max Activating Token Index: 606

Text #13

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2707. Min Act: -0.0001

Data Index: 521860 (C4 (Web Text))

Max Activating Token Index: 926

Text #14

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2758. Min Act: -0.0001

Data Index: 721619 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2796. Min Act: -0.0001

Data Index: 817251 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2844. Min Act: -0.0001

Data Index: 295811 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2907. Min Act: -0.0001

Data Index: 1026041 (C4 (Web Text))

Max Activating Token Index: 657

Text #18

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2622. Min Act: -0.0001

Data Index: 720804 (C4 (Web Text))

Max Activating Token Index: 869

Text #19

Max Range: 0.3197. Min Range: -0.3197

Max Act: 0.2667. Min Act: -0.0001

Data Index: 370962 (C4 (Web Text))

Max Activating Token Index: 172