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

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

Neuron 1610 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: 3.9227. Min Range: -3.9227

Max Act: 3.7264. Min Act: -0.0000

Data Index: 550532 (C4 (Web Text))

Max Activating Token Index: 867

Text #1

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.9227. Min Act: -0.0000

Data Index: 1035194 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.6522. Min Act: -0.0000

Data Index: 985866 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.5049. Min Act: -0.0000

Data Index: 1006555 (C4 (Web Text))

Max Activating Token Index: 622

Text #4

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4635. Min Act: -0.0000

Data Index: 153930 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.6219. Min Act: -0.0000

Data Index: 601845 (C4 (Web Text))

Max Activating Token Index: 440

Text #6

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.6206. Min Act: -0.0000

Data Index: 940253 (C4 (Web Text))

Max Activating Token Index: 813

Text #7

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.7536. Min Act: -0.0000

Data Index: 708490 (C4 (Web Text))

Max Activating Token Index: 890

Text #8

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4382. Min Act: -0.0000

Data Index: 152404 (C4 (Web Text))

Max Activating Token Index: 303

Text #9

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4171. Min Act: -0.0000

Data Index: 71675 (C4 (Web Text))

Max Activating Token Index: 200

Text #10

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.5704. Min Act: -0.0000

Data Index: 905036 (C4 (Web Text))

Max Activating Token Index: 595

Text #11

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.5190. Min Act: -0.0000

Data Index: 907269 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.6520. Min Act: -0.0000

Data Index: 82487 (C4 (Web Text))

Max Activating Token Index: 267

Text #13

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4521. Min Act: -0.0000

Data Index: 7076 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.3253. Min Act: -0.0000

Data Index: 21483 (C4 (Web Text))

Max Activating Token Index: 227

Text #15

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4704. Min Act: -0.0000

Data Index: 368586 (C4 (Web Text))

Max Activating Token Index: 398

Text #16

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4679. Min Act: -0.0000

Data Index: 123504 (C4 (Web Text))

Max Activating Token Index: 359

Text #17

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.4633. Min Act: -0.0000

Data Index: 85066 (C4 (Web Text))

Max Activating Token Index: 884

Text #18

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.3896. Min Act: -0.0000

Data Index: 217321 (C4 (Web Text))

Max Activating Token Index: 259

Text #19

Max Range: 3.9227. Min Range: -3.9227

Max Act: 3.5689. Min Act: -0.0000

Data Index: 615178 (C4 (Web Text))

Max Activating Token Index: 112