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

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

Neuron 4321 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0209. Min Range: -1.0209

Max Act: 1.0209. Min Act: -0.0000

Data Index: 1294573 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.9665. Min Act: -0.0000

Data Index: 361615 (C4 (Web Text))

Max Activating Token Index: 695

Text #2

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.8202. Min Act: -0.0000

Data Index: 1196898 (C4 (Web Text))

Max Activating Token Index: 920

Text #3

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7740. Min Act: -0.0000

Data Index: 934450 (C4 (Web Text))

Max Activating Token Index: 603

Text #4

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7694. Min Act: -0.0000

Data Index: 984844 (C4 (Web Text))

Max Activating Token Index: 225

Text #5

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7937. Min Act: -0.0000

Data Index: 97892 (C4 (Web Text))

Max Activating Token Index: 502

Text #6

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.8376. Min Act: -0.0000

Data Index: 561093 (C4 (Web Text))

Max Activating Token Index: 788

Text #7

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7891. Min Act: -0.0000

Data Index: 313364 (C4 (Web Text))

Max Activating Token Index: 271

Text #8

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7891. Min Act: -0.0000

Data Index: 457310 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.8150. Min Act: -0.0000

Data Index: 1342864 (C4 (Web Text))

Max Activating Token Index: 672

Text #10

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7522. Min Act: -0.0000

Data Index: 1111161 (C4 (Web Text))

Max Activating Token Index: 382

Text #11

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7218. Min Act: -0.0000

Data Index: 1190873 (C4 (Web Text))

Max Activating Token Index: 347

Text #12

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.6970. Min Act: -0.0000

Data Index: 795834 (C4 (Web Text))

Max Activating Token Index: 344

Text #13

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7624. Min Act: -0.0000

Data Index: 920736 (C4 (Web Text))

Max Activating Token Index: 1009

Text #14

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7781. Min Act: -0.0000

Data Index: 879138 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7112. Min Act: -0.0000

Data Index: 341192 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7286. Min Act: -0.0000

Data Index: 479952 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7551. Min Act: -0.0000

Data Index: 1078971 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7182. Min Act: -0.0000

Data Index: 541617 (C4 (Web Text))

Max Activating Token Index: 275

Text #19

Max Range: 1.0209. Min Range: -1.0209

Max Act: 0.7096. Min Act: -0.0000

Data Index: 504576 (C4 (Web Text))

Max Activating Token Index: 788