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

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

Neuron 1518 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.9279. Min Act: -0.0000

Data Index: 941945 (C4 (Web Text))

Max Activating Token Index: 856

Text #1

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.4965. Min Act: -0.0000

Data Index: 621025 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.4538. Min Act: -0.0000

Data Index: 190853 (C4 (Web Text))

Max Activating Token Index: 829

Text #3

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.4321. Min Act: -0.0000

Data Index: 1337878 (C4 (Web Text))

Max Activating Token Index: 829

Text #4

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.4105. Min Act: -0.0000

Data Index: 341149 (C4 (Web Text))

Max Activating Token Index: 834

Text #5

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.4036. Min Act: -0.0000

Data Index: 1628216 (Python Code)

Max Activating Token Index: 198

Text #6

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.4175. Min Act: -0.0000

Data Index: 879229 (C4 (Web Text))

Max Activating Token Index: 962

Text #7

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.4044. Min Act: -0.0000

Data Index: 102784 (C4 (Web Text))

Max Activating Token Index: 174

Text #8

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3544. Min Act: -0.0000

Data Index: 1098353 (C4 (Web Text))

Max Activating Token Index: 444

Text #9

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3801. Min Act: -0.0000

Data Index: 17254 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.2955. Min Act: -0.0000

Data Index: 260978 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3526. Min Act: -0.0000

Data Index: 997842 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3206. Min Act: -0.0000

Data Index: 272801 (C4 (Web Text))

Max Activating Token Index: 941

Text #13

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3517. Min Act: -0.0000

Data Index: 911328 (C4 (Web Text))

Max Activating Token Index: 549

Text #14

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.2746. Min Act: -0.0000

Data Index: 194131 (C4 (Web Text))

Max Activating Token Index: 974

Text #15

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1237082 (C4 (Web Text))

Max Activating Token Index: 208

Text #16

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3196. Min Act: -0.0000

Data Index: 199974 (C4 (Web Text))

Max Activating Token Index: 465

Text #17

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3077. Min Act: -0.0000

Data Index: 88327 (C4 (Web Text))

Max Activating Token Index: 50

Text #18

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.2857. Min Act: -0.0000

Data Index: 803482 (C4 (Web Text))

Max Activating Token Index: 268

Text #19

Max Range: 0.9279. Min Range: -0.9279

Max Act: 0.3207. Min Act: -0.0000

Data Index: 1188229 (C4 (Web Text))

Max Activating Token Index: 928