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

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

Neuron 4290 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: 2.0283. Min Range: -2.0283

Max Act: 2.0283. Min Act: -0.0000

Data Index: 39682 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.6637. Min Act: -0.0000

Data Index: 1259135 (C4 (Web Text))

Max Activating Token Index: 994

Text #2

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.7631. Min Act: 0.0000

Data Index: 1013347 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.6641. Min Act: -0.0000

Data Index: 243201 (C4 (Web Text))

Max Activating Token Index: 999

Text #4

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.4091. Min Act: -0.0000

Data Index: 422970 (C4 (Web Text))

Max Activating Token Index: 888

Text #5

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.4045. Min Act: -0.0000

Data Index: 1146830 (C4 (Web Text))

Max Activating Token Index: 924

Text #6

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.4437. Min Act: -0.0000

Data Index: 687773 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.3476. Min Act: -0.0000

Data Index: 665190 (C4 (Web Text))

Max Activating Token Index: 488

Text #8

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.2769. Min Act: -0.0000

Data Index: 391889 (C4 (Web Text))

Max Activating Token Index: 582

Text #9

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.2727. Min Act: -0.0000

Data Index: 670770 (C4 (Web Text))

Max Activating Token Index: 174

Text #10

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.4357. Min Act: -0.0000

Data Index: 690813 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.4247. Min Act: -0.0000

Data Index: 302454 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.4226. Min Act: -0.0000

Data Index: 259707 (C4 (Web Text))

Max Activating Token Index: 841

Text #13

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.2568. Min Act: -0.0000

Data Index: 1185639 (C4 (Web Text))

Max Activating Token Index: 876

Text #14

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.3152. Min Act: -0.0000

Data Index: 1308147 (C4 (Web Text))

Max Activating Token Index: 767

Text #15

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.2325. Min Act: -0.0000

Data Index: 167881 (C4 (Web Text))

Max Activating Token Index: 72

Text #16

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.2528. Min Act: -0.0000

Data Index: 1024421 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.1835. Min Act: 0.0000

Data Index: 297307 (C4 (Web Text))

Max Activating Token Index: 27

Text #18

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.2579. Min Act: 0.0000

Data Index: 731294 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 2.0283. Min Range: -2.0283

Max Act: 1.3127. Min Act: -0.0000

Data Index: 771686 (C4 (Web Text))

Max Activating Token Index: 623