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

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

Neuron 4449 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.2166. Min Act: -0.0001

Data Index: 1165849 (C4 (Web Text))

Max Activating Token Index: 530

Text #1

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0278. Min Act: -0.0001

Data Index: 1012875 (C4 (Web Text))

Max Activating Token Index: 575

Text #2

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0314. Min Act: -0.0001

Data Index: 306437 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.2166. Min Range: -1.2166

Max Act: 1.0857. Min Act: -0.0001

Data Index: 491422 (C4 (Web Text))

Max Activating Token Index: 387

Text #4

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9869. Min Act: -0.0001

Data Index: 841887 (C4 (Web Text))

Max Activating Token Index: 779

Text #5

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9607. Min Act: -0.0001

Data Index: 171885 (C4 (Web Text))

Max Activating Token Index: 287

Text #6

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9329. Min Act: -0.0001

Data Index: 776009 (C4 (Web Text))

Max Activating Token Index: 925

Text #7

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9714. Min Act: -0.0001

Data Index: 452357 (C4 (Web Text))

Max Activating Token Index: 41

Text #8

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9276. Min Act: -0.0001

Data Index: 426320 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9531. Min Act: -0.0001

Data Index: 717487 (C4 (Web Text))

Max Activating Token Index: 951

Text #10

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9470. Min Act: -0.0000

Data Index: 928148 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9152. Min Act: -0.0001

Data Index: 290696 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9310. Min Act: -0.0000

Data Index: 9066 (C4 (Web Text))

Max Activating Token Index: 923

Text #13

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8787. Min Act: -0.0001

Data Index: 884652 (C4 (Web Text))

Max Activating Token Index: 636

Text #14

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9276. Min Act: -0.0001

Data Index: 298997 (C4 (Web Text))

Max Activating Token Index: 612

Text #15

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9225. Min Act: -0.0001

Data Index: 1315418 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.9198. Min Act: -0.0001

Data Index: 548650 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8766. Min Act: -0.0001

Data Index: 510275 (C4 (Web Text))

Max Activating Token Index: 653

Text #18

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8790. Min Act: -0.0001

Data Index: 930507 (C4 (Web Text))

Max Activating Token Index: 380

Text #19

Max Range: 1.2166. Min Range: -1.2166

Max Act: 0.8828. Min Act: -0.0001

Data Index: 1045971 (C4 (Web Text))

Max Activating Token Index: 968