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

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

Neuron 3762 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3187. Min Range: -2.3187

Max Act: 2.3187. Min Act: -0.0000

Data Index: 256297 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 2.3187. Min Range: -2.3187

Max Act: 2.2066. Min Act: -0.0000

Data Index: 223548 (C4 (Web Text))

Max Activating Token Index: 122

Text #2

Max Range: 2.3187. Min Range: -2.3187

Max Act: 2.0462. Min Act: -0.0000

Data Index: 699510 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 2.3187. Min Range: -2.3187

Max Act: 2.1598. Min Act: -0.0000

Data Index: 823991 (C4 (Web Text))

Max Activating Token Index: 423

Text #4

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.9536. Min Act: -0.0000

Data Index: 338358 (C4 (Web Text))

Max Activating Token Index: 538

Text #5

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.8984. Min Act: -0.0000

Data Index: 1206583 (C4 (Web Text))

Max Activating Token Index: 805

Text #6

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.8080. Min Act: -0.0000

Data Index: 53326 (C4 (Web Text))

Max Activating Token Index: 556

Text #7

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.6274. Min Act: -0.0000

Data Index: 900989 (C4 (Web Text))

Max Activating Token Index: 995

Text #8

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.7181. Min Act: -0.0000

Data Index: 37409 (C4 (Web Text))

Max Activating Token Index: 477

Text #9

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.6694. Min Act: -0.0000

Data Index: 922091 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.4649. Min Act: -0.0000

Data Index: 1026630 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.3681. Min Act: -0.0000

Data Index: 969388 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.3894. Min Act: -0.0000

Data Index: 48500 (C4 (Web Text))

Max Activating Token Index: 565

Text #13

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.2966. Min Act: -0.0000

Data Index: 870274 (C4 (Web Text))

Max Activating Token Index: 124

Text #14

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.4523. Min Act: -0.0000

Data Index: 552680 (C4 (Web Text))

Max Activating Token Index: 818

Text #15

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.3450. Min Act: -0.0000

Data Index: 525100 (C4 (Web Text))

Max Activating Token Index: 631

Text #16

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.3459. Min Act: -0.0000

Data Index: 376001 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.3267. Min Act: -0.0000

Data Index: 931786 (C4 (Web Text))

Max Activating Token Index: 413

Text #18

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.3739. Min Act: -0.0000

Data Index: 255401 (C4 (Web Text))

Max Activating Token Index: 618

Text #19

Max Range: 2.3187. Min Range: -2.3187

Max Act: 1.2901. Min Act: -0.0000

Data Index: 745250 (C4 (Web Text))

Max Activating Token Index: 53