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

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

Neuron 91 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: 3.8640. Min Range: -3.8640

Max Act: 3.7959. Min Act: -0.0000

Data Index: 655697 (C4 (Web Text))

Max Activating Token Index: 222

Text #1

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.5260. Min Act: -0.0000

Data Index: 1501248 (Python Code)

Max Activating Token Index: 716

Text #2

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7286. Min Act: -0.0000

Data Index: 1312835 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.8640. Min Act: -0.0000

Data Index: 723602 (C4 (Web Text))

Max Activating Token Index: 190

Text #4

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.6312. Min Act: -0.0000

Data Index: 1512187 (Python Code)

Max Activating Token Index: 358

Text #5

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.6092. Min Act: -0.0000

Data Index: 1387540 (Python Code)

Max Activating Token Index: 467

Text #6

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.5635. Min Act: -0.0000

Data Index: 811721 (C4 (Web Text))

Max Activating Token Index: 132

Text #7

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.5240. Min Act: -0.0000

Data Index: 976193 (C4 (Web Text))

Max Activating Token Index: 223

Text #8

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.6475. Min Act: -0.0000

Data Index: 1200847 (C4 (Web Text))

Max Activating Token Index: 933

Text #9

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.4474. Min Act: -0.0000

Data Index: 942264 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.6041. Min Act: -0.0000

Data Index: 729416 (C4 (Web Text))

Max Activating Token Index: 287

Text #11

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.4319. Min Act: -0.0000

Data Index: 1071845 (C4 (Web Text))

Max Activating Token Index: 313

Text #12

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.2515. Min Act: -0.0000

Data Index: 951349 (C4 (Web Text))

Max Activating Token Index: 217

Text #13

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.7049. Min Act: -0.0000

Data Index: 338519 (C4 (Web Text))

Max Activating Token Index: 187

Text #14

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.2380. Min Act: -0.0000

Data Index: 143482 (C4 (Web Text))

Max Activating Token Index: 384

Text #15

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.3620. Min Act: -0.0000

Data Index: 349390 (C4 (Web Text))

Max Activating Token Index: 924

Text #16

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.4951. Min Act: -0.0000

Data Index: 315195 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.3373. Min Act: -0.0000

Data Index: 758275 (C4 (Web Text))

Max Activating Token Index: 502

Text #18

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.1557. Min Act: -0.0000

Data Index: 532828 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 3.8640. Min Range: -3.8640

Max Act: 3.3013. Min Act: -0.0000

Data Index: 574398 (C4 (Web Text))

Max Activating Token Index: 254