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

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

Neuron 3794 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: 1.4344. Min Range: -1.4344

Max Act: 1.3998. Min Act: -0.0000

Data Index: 895981 (C4 (Web Text))

Max Activating Token Index: 355

Text #1

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.1641. Min Act: -0.0000

Data Index: 928608 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.1723. Min Act: -0.0000

Data Index: 978369 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.2908. Min Act: -0.0000

Data Index: 279768 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.1470. Min Act: -0.0000

Data Index: 846534 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.1712. Min Act: -0.0000

Data Index: 142440 (C4 (Web Text))

Max Activating Token Index: 478

Text #6

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.1243. Min Act: -0.0000

Data Index: 1349479 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.4344. Min Act: -0.0000

Data Index: 3181 (C4 (Web Text))

Max Activating Token Index: 209

Text #8

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.0169. Min Act: -0.0000

Data Index: 869333 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.0230. Min Act: -0.0000

Data Index: 323949 (C4 (Web Text))

Max Activating Token Index: 31

Text #10

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.0183. Min Act: -0.0000

Data Index: 460559 (C4 (Web Text))

Max Activating Token Index: 78

Text #11

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.0005. Min Act: -0.0000

Data Index: 735174 (C4 (Web Text))

Max Activating Token Index: 606

Text #12

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9393. Min Act: -0.0000

Data Index: 431519 (C4 (Web Text))

Max Activating Token Index: 251

Text #13

Max Range: 1.4344. Min Range: -1.4344

Max Act: 1.0020. Min Act: -0.0000

Data Index: 1268824 (C4 (Web Text))

Max Activating Token Index: 308

Text #14

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9178. Min Act: -0.0000

Data Index: 10891 (C4 (Web Text))

Max Activating Token Index: 658

Text #15

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.8861. Min Act: -0.0000

Data Index: 402071 (C4 (Web Text))

Max Activating Token Index: 38

Text #16

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.8615. Min Act: -0.0000

Data Index: 196407 (C4 (Web Text))

Max Activating Token Index: 52

Text #17

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.9075. Min Act: -0.0000

Data Index: 148555 (C4 (Web Text))

Max Activating Token Index: 458

Text #18

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.8311. Min Act: -0.0000

Data Index: 1045484 (C4 (Web Text))

Max Activating Token Index: 829

Text #19

Max Range: 1.4344. Min Range: -1.4344

Max Act: 0.8241. Min Act: -0.0000

Data Index: 1104383 (C4 (Web Text))

Max Activating Token Index: 287