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

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

Neuron 2712 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.7772. Min Act: -0.0000

Data Index: 271792 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.4320. Min Act: -0.0000

Data Index: 102184 (C4 (Web Text))

Max Activating Token Index: 653

Text #2

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.4427. Min Act: -0.0000

Data Index: 1099747 (C4 (Web Text))

Max Activating Token Index: 842

Text #3

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.4050. Min Act: -0.0000

Data Index: 1138337 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3677. Min Act: -0.0000

Data Index: 295584 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3804. Min Act: -0.0000

Data Index: 485810 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3565. Min Act: -0.0000

Data Index: 795854 (C4 (Web Text))

Max Activating Token Index: 367

Text #7

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3471. Min Act: -0.0000

Data Index: 573753 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3404. Min Act: -0.0000

Data Index: 726438 (C4 (Web Text))

Max Activating Token Index: 10

Text #9

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3388. Min Act: -0.0000

Data Index: 631640 (C4 (Web Text))

Max Activating Token Index: 875

Text #10

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3963. Min Act: -0.0000

Data Index: 442994 (C4 (Web Text))

Max Activating Token Index: 343

Text #11

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.4131. Min Act: -0.0000

Data Index: 926176 (C4 (Web Text))

Max Activating Token Index: 296

Text #12

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3029. Min Act: -0.0000

Data Index: 890038 (C4 (Web Text))

Max Activating Token Index: 1011

Text #13

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3021. Min Act: -0.0000

Data Index: 756757 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.2220. Min Act: -0.0000

Data Index: 723467 (C4 (Web Text))

Max Activating Token Index: 91

Text #15

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.2846. Min Act: -0.0000

Data Index: 1317168 (C4 (Web Text))

Max Activating Token Index: 389

Text #16

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.3177. Min Act: -0.0000

Data Index: 663613 (C4 (Web Text))

Max Activating Token Index: 61

Text #17

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.2376. Min Act: -0.0000

Data Index: 250667 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.2585. Min Act: -0.0000

Data Index: 620688 (C4 (Web Text))

Max Activating Token Index: 320

Text #19

Max Range: 1.7772. Min Range: -1.7772

Max Act: 1.2657. Min Act: -0.0000

Data Index: 760370 (C4 (Web Text))

Max Activating Token Index: 556