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

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

Neuron 2972 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.5128. Min Act: -0.0000

Data Index: 976625 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.5274. Min Act: -0.0000

Data Index: 88925 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.2735. Min Act: -0.0000

Data Index: 701258 (C4 (Web Text))

Max Activating Token Index: 576

Text #3

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.2596. Min Act: -0.0000

Data Index: 905380 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.3327. Min Act: -0.0000

Data Index: 418255 (C4 (Web Text))

Max Activating Token Index: 361

Text #5

Max Range: 3.5274. Min Range: -3.5274

Max Act: 3.0330. Min Act: -0.0000

Data Index: 979869 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.8097. Min Act: -0.0000

Data Index: 1349186 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.6177. Min Act: -0.0000

Data Index: 1227899 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.5599. Min Act: -0.0000

Data Index: 745595 (C4 (Web Text))

Max Activating Token Index: 423

Text #9

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.6253. Min Act: -0.0000

Data Index: 168911 (C4 (Web Text))

Max Activating Token Index: 649

Text #10

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.5828. Min Act: -0.0000

Data Index: 980560 (C4 (Web Text))

Max Activating Token Index: 500

Text #11

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.6985. Min Act: -0.0000

Data Index: 1218757 (C4 (Web Text))

Max Activating Token Index: 312

Text #12

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.4362. Min Act: -0.0000

Data Index: 1127858 (C4 (Web Text))

Max Activating Token Index: 282

Text #13

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.5706. Min Act: -0.0000

Data Index: 212630 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.3166. Min Act: -0.0000

Data Index: 1613846 (Python Code)

Max Activating Token Index: 640

Text #15

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.2367. Min Act: -0.0000

Data Index: 1242328 (C4 (Web Text))

Max Activating Token Index: 523

Text #16

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.3708. Min Act: -0.0000

Data Index: 795116 (C4 (Web Text))

Max Activating Token Index: 240

Text #17

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.5083. Min Act: -0.0000

Data Index: 1348091 (C4 (Web Text))

Max Activating Token Index: 380

Text #18

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.4355. Min Act: -0.0000

Data Index: 755002 (C4 (Web Text))

Max Activating Token Index: 715

Text #19

Max Range: 3.5274. Min Range: -3.5274

Max Act: 2.1205. Min Act: -0.0000

Data Index: 1423984 (Python Code)

Max Activating Token Index: 463