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

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

Neuron 1717 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.4130. Min Range: -2.4130

Max Act: 2.4130. Min Act: -0.0000

Data Index: 143739 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.5686. Min Act: -0.0000

Data Index: 1186649 (C4 (Web Text))

Max Activating Token Index: 195

Text #2

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.5987. Min Act: -0.0000

Data Index: 590374 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.5534. Min Act: -0.0000

Data Index: 42445 (C4 (Web Text))

Max Activating Token Index: 193

Text #4

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.4444. Min Act: -0.0000

Data Index: 763149 (C4 (Web Text))

Max Activating Token Index: 58

Text #5

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.3800. Min Act: -0.0000

Data Index: 953313 (C4 (Web Text))

Max Activating Token Index: 282

Text #6

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.4382. Min Act: -0.0000

Data Index: 523121 (C4 (Web Text))

Max Activating Token Index: 415

Text #7

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.3726. Min Act: -0.0000

Data Index: 310584 (C4 (Web Text))

Max Activating Token Index: 930

Text #8

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.3219. Min Act: -0.0000

Data Index: 878202 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.3173. Min Act: -0.0000

Data Index: 209104 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.3320. Min Act: -0.0000

Data Index: 834629 (C4 (Web Text))

Max Activating Token Index: 164

Text #11

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.3391. Min Act: -0.0001

Data Index: 1210274 (C4 (Web Text))

Max Activating Token Index: 509

Text #12

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.3253. Min Act: -0.0001

Data Index: 1045798 (C4 (Web Text))

Max Activating Token Index: 145

Text #13

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.2656. Min Act: -0.0001

Data Index: 305856 (C4 (Web Text))

Max Activating Token Index: 34

Text #14

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.2246. Min Act: -0.0000

Data Index: 596119 (C4 (Web Text))

Max Activating Token Index: 171

Text #15

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.2161. Min Act: -0.0001

Data Index: 1217949 (C4 (Web Text))

Max Activating Token Index: 203

Text #16

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.2303. Min Act: -0.0000

Data Index: 731504 (C4 (Web Text))

Max Activating Token Index: 234

Text #17

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.2570. Min Act: -0.0000

Data Index: 1244332 (C4 (Web Text))

Max Activating Token Index: 26

Text #18

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.1722. Min Act: -0.0000

Data Index: 629443 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 2.4130. Min Range: -2.4130

Max Act: 1.1496. Min Act: -0.0001

Data Index: 114194 (C4 (Web Text))

Max Activating Token Index: 597