Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5563 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.8251. Min Act: -0.0000

Data Index: 1166969 (C4 (Web Text))

Max Activating Token Index: 461

Text #1

Max Range: 2.0161. Min Range: -2.0161

Max Act: 2.0161. Min Act: -0.0000

Data Index: 1095539 (C4 (Web Text))

Max Activating Token Index: 160

Text #2

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.9027. Min Act: -0.0000

Data Index: 548248 (C4 (Web Text))

Max Activating Token Index: 366

Text #3

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.9738. Min Act: -0.0000

Data Index: 628484 (C4 (Web Text))

Max Activating Token Index: 277

Text #4

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.7695. Min Act: -0.0000

Data Index: 1262168 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.5937. Min Act: -0.0000

Data Index: 127005 (C4 (Web Text))

Max Activating Token Index: 270

Text #6

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.8248. Min Act: -0.0000

Data Index: 185811 (C4 (Web Text))

Max Activating Token Index: 431

Text #7

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1356509 (C4 (Web Text))

Max Activating Token Index: 578

Text #8

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.5809. Min Act: -0.0000

Data Index: 174186 (C4 (Web Text))

Max Activating Token Index: 601

Text #9

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.5479. Min Act: -0.0000

Data Index: 1339902 (C4 (Web Text))

Max Activating Token Index: 53

Text #10

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.7294. Min Act: -0.0000

Data Index: 1107558 (C4 (Web Text))

Max Activating Token Index: 472

Text #11

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.7290. Min Act: -0.0000

Data Index: 461011 (C4 (Web Text))

Max Activating Token Index: 787

Text #12

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.6227. Min Act: -0.0000

Data Index: 73805 (C4 (Web Text))

Max Activating Token Index: 146

Text #13

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.6965. Min Act: -0.0000

Data Index: 297186 (C4 (Web Text))

Max Activating Token Index: 148

Text #14

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.6044. Min Act: -0.0000

Data Index: 756073 (C4 (Web Text))

Max Activating Token Index: 62

Text #15

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.4049. Min Act: -0.0000

Data Index: 671421 (C4 (Web Text))

Max Activating Token Index: 354

Text #16

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.7759. Min Act: -0.0000

Data Index: 379598 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.4626. Min Act: -0.0000

Data Index: 928531 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.5779. Min Act: -0.0000

Data Index: 351323 (C4 (Web Text))

Max Activating Token Index: 122

Text #19

Max Range: 2.0161. Min Range: -2.0161

Max Act: 1.5639. Min Act: -0.0000

Data Index: 687250 (C4 (Web Text))

Max Activating Token Index: 69