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

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

Neuron 2196 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: 1.4440. Min Range: -1.4440

Max Act: 1.4440. Min Act: -0.0000

Data Index: 1154166 (C4 (Web Text))

Max Activating Token Index: 957

Text #1

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.3026. Min Act: -0.0000

Data Index: 790946 (C4 (Web Text))

Max Activating Token Index: 229

Text #2

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.1980. Min Act: -0.0000

Data Index: 1319574 (C4 (Web Text))

Max Activating Token Index: 324

Text #3

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.1891. Min Act: -0.0000

Data Index: 502828 (C4 (Web Text))

Max Activating Token Index: 1018

Text #4

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.0626. Min Act: -0.0000

Data Index: 1312163 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.0206. Min Act: -0.0000

Data Index: 4502 (C4 (Web Text))

Max Activating Token Index: 191

Text #6

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1060365 (C4 (Web Text))

Max Activating Token Index: 453

Text #7

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1449296 (Python Code)

Max Activating Token Index: 590

Text #8

Max Range: 1.4440. Min Range: -1.4440

Max Act: 0.9128. Min Act: -0.0000

Data Index: 179182 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.0034. Min Act: -0.0000

Data Index: 174885 (C4 (Web Text))

Max Activating Token Index: 493

Text #10

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.0487. Min Act: -0.0000

Data Index: 378126 (C4 (Web Text))

Max Activating Token Index: 960

Text #11

Max Range: 1.4440. Min Range: -1.4440

Max Act: 0.9694. Min Act: -0.0000

Data Index: 665173 (C4 (Web Text))

Max Activating Token Index: 980

Text #12

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.0265. Min Act: -0.0000

Data Index: 61073 (C4 (Web Text))

Max Activating Token Index: 593

Text #13

Max Range: 1.4440. Min Range: -1.4440

Max Act: 1.0057. Min Act: -0.0000

Data Index: 269080 (C4 (Web Text))

Max Activating Token Index: 284

Text #14

Max Range: 1.4440. Min Range: -1.4440

Max Act: 0.9694. Min Act: -0.0000

Data Index: 1202274 (C4 (Web Text))

Max Activating Token Index: 388

Text #15

Max Range: 1.4440. Min Range: -1.4440

Max Act: 0.9222. Min Act: -0.0000

Data Index: 522529 (C4 (Web Text))

Max Activating Token Index: 224

Text #16

Max Range: 1.4440. Min Range: -1.4440

Max Act: 0.9553. Min Act: -0.0000

Data Index: 1051391 (C4 (Web Text))

Max Activating Token Index: 318

Text #17

Max Range: 1.4440. Min Range: -1.4440

Max Act: 0.9453. Min Act: -0.0000

Data Index: 362379 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 1.4440. Min Range: -1.4440

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1297132 (C4 (Web Text))

Max Activating Token Index: 12

Text #19

Max Range: 1.4440. Min Range: -1.4440

Max Act: 0.8941. Min Act: -0.0000

Data Index: 187824 (C4 (Web Text))

Max Activating Token Index: 921