Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1775 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1079703 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.6315. Min Act: -0.0000

Data Index: 575120 (C4 (Web Text))

Max Activating Token Index: 474

Text #2

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.5215. Min Act: -0.0000

Data Index: 220783 (C4 (Web Text))

Max Activating Token Index: 767

Text #3

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.5107. Min Act: -0.0000

Data Index: 559100 (C4 (Web Text))

Max Activating Token Index: 20

Text #4

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4874. Min Act: -0.0000

Data Index: 1358597 (C4 (Web Text))

Max Activating Token Index: 87

Text #5

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4688. Min Act: -0.0000

Data Index: 1092076 (C4 (Web Text))

Max Activating Token Index: 803

Text #6

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4574. Min Act: -0.0001

Data Index: 1347233 (C4 (Web Text))

Max Activating Token Index: 700

Text #7

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4698. Min Act: -0.0000

Data Index: 401539 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4437. Min Act: -0.0001

Data Index: 1104750 (C4 (Web Text))

Max Activating Token Index: 520

Text #9

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4558. Min Act: 0.0000

Data Index: 687510 (C4 (Web Text))

Max Activating Token Index: 156

Text #10

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4498. Min Act: -0.0000

Data Index: 1114821 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4483. Min Act: -0.0001

Data Index: 50712 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4571. Min Act: -0.0000

Data Index: 1008758 (C4 (Web Text))

Max Activating Token Index: 527

Text #13

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4248. Min Act: -0.0000

Data Index: 888028 (C4 (Web Text))

Max Activating Token Index: 682

Text #14

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4566. Min Act: -0.0000

Data Index: 1353617 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4375. Min Act: -0.0000

Data Index: 381414 (C4 (Web Text))

Max Activating Token Index: 852

Text #16

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4392. Min Act: -0.0000

Data Index: 1002057 (C4 (Web Text))

Max Activating Token Index: 572

Text #17

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1096493 (C4 (Web Text))

Max Activating Token Index: 214

Text #18

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1041167 (C4 (Web Text))

Max Activating Token Index: 820

Text #19

Max Range: 0.6315. Min Range: -0.6315

Max Act: 0.4185. Min Act: -0.0001

Data Index: 880640 (C4 (Web Text))

Max Activating Token Index: 513