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

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

Neuron 4754 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: 1.0271. Min Range: -1.0271

Max Act: 1.0132. Min Act: -0.0000

Data Index: 693547 (C4 (Web Text))

Max Activating Token Index: 819

Text #1

Max Range: 1.0271. Min Range: -1.0271

Max Act: 1.0271. Min Act: -0.0000

Data Index: 268215 (C4 (Web Text))

Max Activating Token Index: 380

Text #2

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.8852. Min Act: -0.0000

Data Index: 188116 (C4 (Web Text))

Max Activating Token Index: 530

Text #3

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.8070. Min Act: -0.0000

Data Index: 829540 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.7240. Min Act: -0.0000

Data Index: 122639 (C4 (Web Text))

Max Activating Token Index: 898

Text #5

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6543. Min Act: -0.0000

Data Index: 515459 (C4 (Web Text))

Max Activating Token Index: 607

Text #6

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6496. Min Act: -0.0000

Data Index: 789724 (C4 (Web Text))

Max Activating Token Index: 953

Text #7

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6368. Min Act: -0.0000

Data Index: 1126204 (C4 (Web Text))

Max Activating Token Index: 845

Text #8

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6093. Min Act: -0.0000

Data Index: 1199279 (C4 (Web Text))

Max Activating Token Index: 609

Text #9

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6630. Min Act: -0.0000

Data Index: 1239076 (C4 (Web Text))

Max Activating Token Index: 615

Text #10

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6586. Min Act: -0.0000

Data Index: 292625 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.5635. Min Act: -0.0000

Data Index: 854200 (C4 (Web Text))

Max Activating Token Index: 952

Text #12

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.5706. Min Act: -0.0000

Data Index: 768601 (C4 (Web Text))

Max Activating Token Index: 621

Text #13

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6718. Min Act: -0.0000

Data Index: 1319107 (C4 (Web Text))

Max Activating Token Index: 997

Text #14

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.5674. Min Act: -0.0000

Data Index: 492534 (C4 (Web Text))

Max Activating Token Index: 783

Text #15

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6135. Min Act: -0.0000

Data Index: 1138469 (C4 (Web Text))

Max Activating Token Index: 25

Text #16

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.5934. Min Act: -0.0000

Data Index: 20374 (C4 (Web Text))

Max Activating Token Index: 507

Text #17

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.5831. Min Act: -0.0000

Data Index: 940295 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6062. Min Act: -0.0000

Data Index: 1009125 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 1.0271. Min Range: -1.0271

Max Act: 0.6199. Min Act: -0.0000

Data Index: 96102 (C4 (Web Text))

Max Activating Token Index: 214