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

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

Neuron 2570 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: 2.3875. Min Range: -2.3875

Max Act: 2.3875. Min Act: -0.0000

Data Index: 1065897 (C4 (Web Text))

Max Activating Token Index: 396

Text #1

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.3328. Min Act: -0.0000

Data Index: 293518 (C4 (Web Text))

Max Activating Token Index: 800

Text #2

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.2443. Min Act: -0.0000

Data Index: 409194 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.2298. Min Act: -0.0000

Data Index: 195784 (C4 (Web Text))

Max Activating Token Index: 341

Text #4

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0376. Min Act: -0.0000

Data Index: 1172138 (C4 (Web Text))

Max Activating Token Index: 368

Text #5

Max Range: 2.3875. Min Range: -2.3875

Max Act: 1.8640. Min Act: -0.0000

Data Index: 627654 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.1322. Min Act: -0.0000

Data Index: 1028668 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.1114. Min Act: -0.0000

Data Index: 562130 (C4 (Web Text))

Max Activating Token Index: 809

Text #8

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0092. Min Act: -0.0000

Data Index: 315304 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0033. Min Act: -0.0000

Data Index: 1003262 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0945. Min Act: -0.0000

Data Index: 148291 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0812. Min Act: -0.0000

Data Index: 783338 (C4 (Web Text))

Max Activating Token Index: 142

Text #12

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0959. Min Act: -0.0000

Data Index: 779779 (C4 (Web Text))

Max Activating Token Index: 598

Text #13

Max Range: 2.3875. Min Range: -2.3875

Max Act: 1.9705. Min Act: -0.0000

Data Index: 525208 (C4 (Web Text))

Max Activating Token Index: 1012

Text #14

Max Range: 2.3875. Min Range: -2.3875

Max Act: 1.9660. Min Act: -0.0000

Data Index: 1075239 (C4 (Web Text))

Max Activating Token Index: 614

Text #15

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0763. Min Act: -0.0000

Data Index: 723027 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0769. Min Act: -0.0000

Data Index: 192641 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 2.3875. Min Range: -2.3875

Max Act: 1.9584. Min Act: -0.0000

Data Index: 301550 (C4 (Web Text))

Max Activating Token Index: 555

Text #18

Max Range: 2.3875. Min Range: -2.3875

Max Act: 1.9368. Min Act: -0.0000

Data Index: 1278475 (C4 (Web Text))

Max Activating Token Index: 976

Text #19

Max Range: 2.3875. Min Range: -2.3875

Max Act: 2.0508. Min Act: -0.0000

Data Index: 1101964 (C4 (Web Text))

Max Activating Token Index: 88