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

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

Neuron 498 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.6370. Min Act: -0.0001

Data Index: 585645 (C4 (Web Text))

Max Activating Token Index: 634

Text #1

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.6016. Min Act: -0.0001

Data Index: 271753 (C4 (Web Text))

Max Activating Token Index: 27

Text #2

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5311. Min Act: -0.0001

Data Index: 544231 (C4 (Web Text))

Max Activating Token Index: 619

Text #3

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5641. Min Act: -0.0001

Data Index: 998291 (C4 (Web Text))

Max Activating Token Index: 10

Text #4

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5237. Min Act: -0.0001

Data Index: 171870 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4701. Min Act: -0.0001

Data Index: 873872 (C4 (Web Text))

Max Activating Token Index: 216

Text #6

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5870. Min Act: -0.0001

Data Index: 1003416 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5666. Min Act: -0.0001

Data Index: 435462 (C4 (Web Text))

Max Activating Token Index: 110

Text #8

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5159. Min Act: -0.0001

Data Index: 487384 (C4 (Web Text))

Max Activating Token Index: 213

Text #9

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4541. Min Act: -0.0001

Data Index: 592181 (C4 (Web Text))

Max Activating Token Index: 170

Text #10

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4807. Min Act: -0.0001

Data Index: 1171861 (C4 (Web Text))

Max Activating Token Index: 127

Text #11

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5055. Min Act: -0.0001

Data Index: 557721 (C4 (Web Text))

Max Activating Token Index: 265

Text #12

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4498. Min Act: -0.0001

Data Index: 345340 (C4 (Web Text))

Max Activating Token Index: 928

Text #13

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4576. Min Act: -0.0001

Data Index: 496322 (C4 (Web Text))

Max Activating Token Index: 884

Text #14

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.5355. Min Act: -0.0001

Data Index: 347383 (C4 (Web Text))

Max Activating Token Index: 150

Text #15

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4401. Min Act: -0.0001

Data Index: 460358 (C4 (Web Text))

Max Activating Token Index: 610

Text #16

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4093. Min Act: -0.0001

Data Index: 955725 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4568. Min Act: -0.0001

Data Index: 278959 (C4 (Web Text))

Max Activating Token Index: 159

Text #18

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.3541. Min Act: -0.0001

Data Index: 982631 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 1.6370. Min Range: -1.6370

Max Act: 1.4297. Min Act: -0.0001

Data Index: 957086 (C4 (Web Text))

Max Activating Token Index: 414