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

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

Neuron 2382 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.6327. Min Act: -0.0000

Data Index: 1100350 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.6189. Min Act: -0.0000

Data Index: 469231 (C4 (Web Text))

Max Activating Token Index: 853

Text #2

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.6077. Min Act: -0.0000

Data Index: 722145 (C4 (Web Text))

Max Activating Token Index: 157

Text #3

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.5593. Min Act: -0.0000

Data Index: 767510 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.5595. Min Act: -0.0000

Data Index: 354132 (C4 (Web Text))

Max Activating Token Index: 77

Text #5

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1152282 (C4 (Web Text))

Max Activating Token Index: 58

Text #6

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.5339. Min Act: -0.0000

Data Index: 69885 (C4 (Web Text))

Max Activating Token Index: 760

Text #7

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.5295. Min Act: -0.0000

Data Index: 1292654 (C4 (Web Text))

Max Activating Token Index: 959

Text #8

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.5113. Min Act: -0.0000

Data Index: 961457 (C4 (Web Text))

Max Activating Token Index: 919

Text #9

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.5084. Min Act: -0.0000

Data Index: 1165370 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4875. Min Act: -0.0000

Data Index: 1055089 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4863. Min Act: -0.0000

Data Index: 285829 (C4 (Web Text))

Max Activating Token Index: 928

Text #12

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4787. Min Act: -0.0000

Data Index: 831813 (C4 (Web Text))

Max Activating Token Index: 392

Text #13

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4956. Min Act: -0.0000

Data Index: 840792 (C4 (Web Text))

Max Activating Token Index: 97

Text #14

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4949. Min Act: -0.0000

Data Index: 23087 (C4 (Web Text))

Max Activating Token Index: 175

Text #15

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4568. Min Act: -0.0000

Data Index: 825893 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4499. Min Act: -0.0000

Data Index: 443472 (C4 (Web Text))

Max Activating Token Index: 338

Text #17

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4375. Min Act: -0.0000

Data Index: 410913 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4334. Min Act: -0.0000

Data Index: 1354716 (C4 (Web Text))

Max Activating Token Index: 141

Text #19

Max Range: 0.6327. Min Range: -0.6327

Max Act: 0.4432. Min Act: -0.0000

Data Index: 441580 (C4 (Web Text))

Max Activating Token Index: 28