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

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

Neuron 3393 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.7925. Min Act: -0.0001

Data Index: 212115 (C4 (Web Text))

Max Activating Token Index: 829

Text #1

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.1383. Min Act: -0.0000

Data Index: 318240 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.2362. Min Act: -0.0001

Data Index: 160539 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.3717. Min Act: -0.0000

Data Index: 378686 (C4 (Web Text))

Max Activating Token Index: 687

Text #4

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.4806. Min Act: -0.0001

Data Index: 171800 (C4 (Web Text))

Max Activating Token Index: 213

Text #5

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.3406. Min Act: -0.0000

Data Index: 1198531 (C4 (Web Text))

Max Activating Token Index: 75

Text #6

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.3056. Min Act: -0.0000

Data Index: 969798 (C4 (Web Text))

Max Activating Token Index: 55

Text #7

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.1019. Min Act: -0.0001

Data Index: 1212877 (C4 (Web Text))

Max Activating Token Index: 984

Text #8

Max Range: 3.7925. Min Range: -3.7925

Max Act: 2.9451. Min Act: -0.0000

Data Index: 1100376 (C4 (Web Text))

Max Activating Token Index: 690

Text #9

Max Range: 3.7925. Min Range: -3.7925

Max Act: 2.7357. Min Act: -0.0001

Data Index: 1103478 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.1490. Min Act: -0.0001

Data Index: 587636 (C4 (Web Text))

Max Activating Token Index: 216

Text #11

Max Range: 3.7925. Min Range: -3.7925

Max Act: 2.8701. Min Act: -0.0001

Data Index: 220705 (C4 (Web Text))

Max Activating Token Index: 342

Text #12

Max Range: 3.7925. Min Range: -3.7925

Max Act: 2.9372. Min Act: -0.0001

Data Index: 1098054 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 3.7925. Min Range: -3.7925

Max Act: 2.6457. Min Act: -0.0000

Data Index: 295719 (C4 (Web Text))

Max Activating Token Index: 681

Text #14

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.0790. Min Act: -0.0001

Data Index: 776782 (C4 (Web Text))

Max Activating Token Index: 582

Text #15

Max Range: 3.7925. Min Range: -3.7925

Max Act: 2.8757. Min Act: -0.0000

Data Index: 435555 (C4 (Web Text))

Max Activating Token Index: 572

Text #16

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.0146. Min Act: -0.0000

Data Index: 31490 (C4 (Web Text))

Max Activating Token Index: 668

Text #17

Max Range: 3.7925. Min Range: -3.7925

Max Act: 3.1114. Min Act: -0.0001

Data Index: 780538 (C4 (Web Text))

Max Activating Token Index: 889

Text #18

Max Range: 3.7925. Min Range: -3.7925

Max Act: 2.5997. Min Act: -0.0001

Data Index: 886984 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 3.7925. Min Range: -3.7925

Max Act: 2.8149. Min Act: -0.0001

Data Index: 722832 (C4 (Web Text))

Max Activating Token Index: 220