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

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

Neuron 3908 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1060329 (C4 (Web Text))

Max Activating Token Index: 841

Text #1

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2846. Min Act: -0.0000

Data Index: 563155 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2777. Min Act: -0.0000

Data Index: 1239360 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2735. Min Act: -0.0000

Data Index: 1022352 (C4 (Web Text))

Max Activating Token Index: 884

Text #4

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2696. Min Act: -0.0000

Data Index: 93370 (C4 (Web Text))

Max Activating Token Index: 752

Text #5

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2630. Min Act: -0.0000

Data Index: 345207 (C4 (Web Text))

Max Activating Token Index: 847

Text #6

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2721. Min Act: -0.0000

Data Index: 920233 (C4 (Web Text))

Max Activating Token Index: 780

Text #7

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2647. Min Act: -0.0000

Data Index: 195950 (C4 (Web Text))

Max Activating Token Index: 107

Text #8

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2400. Min Act: -0.0000

Data Index: 863693 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2556. Min Act: -0.0000

Data Index: 243723 (C4 (Web Text))

Max Activating Token Index: 632

Text #10

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2566. Min Act: -0.0000

Data Index: 67832 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2479. Min Act: -0.0000

Data Index: 400625 (C4 (Web Text))

Max Activating Token Index: 858

Text #12

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2524. Min Act: -0.0000

Data Index: 850714 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2347. Min Act: -0.0000

Data Index: 741917 (C4 (Web Text))

Max Activating Token Index: 972

Text #14

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1259780 (C4 (Web Text))

Max Activating Token Index: 823

Text #15

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2473. Min Act: -0.0000

Data Index: 74669 (C4 (Web Text))

Max Activating Token Index: 692

Text #16

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2283. Min Act: -0.0000

Data Index: 76330 (C4 (Web Text))

Max Activating Token Index: 985

Text #17

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2280. Min Act: -0.0000

Data Index: 468367 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2229. Min Act: -0.0000

Data Index: 301419 (C4 (Web Text))

Max Activating Token Index: 890

Text #19

Max Range: 0.4354. Min Range: -0.4354

Max Act: 0.2312. Min Act: -0.0000

Data Index: 1161528 (C4 (Web Text))

Max Activating Token Index: 104