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

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

Neuron 5850 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.3380. Min Act: -0.0000

Data Index: 1101449 (C4 (Web Text))

Max Activating Token Index: 908

Text #1

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.3361. Min Act: -0.0000

Data Index: 1121986 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.3110. Min Act: -0.0000

Data Index: 986243 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2781. Min Act: -0.0000

Data Index: 364478 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2733. Min Act: -0.0000

Data Index: 996862 (C4 (Web Text))

Max Activating Token Index: 646

Text #5

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2885. Min Act: -0.0000

Data Index: 1236702 (C4 (Web Text))

Max Activating Token Index: 192

Text #6

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2783. Min Act: -0.0000

Data Index: 835072 (C4 (Web Text))

Max Activating Token Index: 538

Text #7

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2803. Min Act: -0.0000

Data Index: 320401 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2716. Min Act: -0.0000

Data Index: 824334 (C4 (Web Text))

Max Activating Token Index: 234

Text #9

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2615. Min Act: -0.0000

Data Index: 597995 (C4 (Web Text))

Max Activating Token Index: 811

Text #10

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2667. Min Act: -0.0000

Data Index: 1051939 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2668. Min Act: -0.0000

Data Index: 1113682 (C4 (Web Text))

Max Activating Token Index: 697

Text #12

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2461. Min Act: -0.0000

Data Index: 791456 (C4 (Web Text))

Max Activating Token Index: 223

Text #13

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2601. Min Act: -0.0000

Data Index: 207365 (C4 (Web Text))

Max Activating Token Index: 601

Text #14

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2512. Min Act: -0.0000

Data Index: 1026444 (C4 (Web Text))

Max Activating Token Index: 159

Text #15

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2574. Min Act: -0.0000

Data Index: 990419 (C4 (Web Text))

Max Activating Token Index: 644

Text #16

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2579. Min Act: -0.0000

Data Index: 1358461 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2563. Min Act: -0.0000

Data Index: 849699 (C4 (Web Text))

Max Activating Token Index: 70

Text #18

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2534. Min Act: -0.0000

Data Index: 471466 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.3380. Min Range: -0.3380

Max Act: 0.2512. Min Act: -0.0000

Data Index: 77913 (C4 (Web Text))

Max Activating Token Index: 979