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

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

Neuron 4573 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3160. Min Act: 0.0001

Data Index: 631932 (C4 (Web Text))

Max Activating Token Index: 403

Text #1

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.3132. Min Act: 0.0001

Data Index: 35675 (C4 (Web Text))

Max Activating Token Index: 783

Text #2

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2912. Min Act: 0.0001

Data Index: 114819 (C4 (Web Text))

Max Activating Token Index: 976

Text #3

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2875. Min Act: -0.0000

Data Index: 835777 (C4 (Web Text))

Max Activating Token Index: 229

Text #4

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2826. Min Act: 0.0001

Data Index: 728278 (C4 (Web Text))

Max Activating Token Index: 692

Text #5

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2796. Min Act: -0.0000

Data Index: 477425 (C4 (Web Text))

Max Activating Token Index: 930

Text #6

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2887. Min Act: -0.0000

Data Index: 66492 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2855. Min Act: -0.0000

Data Index: 29519 (C4 (Web Text))

Max Activating Token Index: 232

Text #8

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2787. Min Act: 0.0000

Data Index: 187838 (C4 (Web Text))

Max Activating Token Index: 82

Text #9

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2659. Min Act: -0.0000

Data Index: 1319849 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2670. Min Act: 0.0001

Data Index: 60558 (C4 (Web Text))

Max Activating Token Index: 118

Text #11

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2619. Min Act: 0.0001

Data Index: 455488 (C4 (Web Text))

Max Activating Token Index: 158

Text #12

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2519. Min Act: 0.0001

Data Index: 501382 (C4 (Web Text))

Max Activating Token Index: 285

Text #13

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2599. Min Act: -0.0000

Data Index: 1340493 (C4 (Web Text))

Max Activating Token Index: 503

Text #14

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2566. Min Act: 0.0001

Data Index: 698264 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2461. Min Act: 0.0001

Data Index: 424761 (C4 (Web Text))

Max Activating Token Index: 57

Text #16

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2542. Min Act: -0.0000

Data Index: 241833 (C4 (Web Text))

Max Activating Token Index: 165

Text #17

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2382. Min Act: -0.0000

Data Index: 912530 (C4 (Web Text))

Max Activating Token Index: 62

Text #18

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2466. Min Act: 0.0001

Data Index: 951881 (C4 (Web Text))

Max Activating Token Index: 871

Text #19

Max Range: 0.3160. Min Range: -0.3160

Max Act: 0.2432. Min Act: 0.0001

Data Index: 1064766 (C4 (Web Text))

Max Activating Token Index: 794