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

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

Neuron 3264 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5156. Min Range: -2.5156

Max Act: 2.5156. Min Act: -0.0000

Data Index: 638726 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 2.5156. Min Range: -2.5156

Max Act: 2.4989. Min Act: -0.0000

Data Index: 467341 (C4 (Web Text))

Max Activating Token Index: 821

Text #2

Max Range: 2.5156. Min Range: -2.5156

Max Act: 2.4299. Min Act: -0.0000

Data Index: 1198396 (C4 (Web Text))

Max Activating Token Index: 492

Text #3

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.9283. Min Act: -0.0000

Data Index: 34182 (C4 (Web Text))

Max Activating Token Index: 714

Text #4

Max Range: 2.5156. Min Range: -2.5156

Max Act: 2.1363. Min Act: -0.0000

Data Index: 552506 (C4 (Web Text))

Max Activating Token Index: 999

Text #5

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.9666. Min Act: -0.0000

Data Index: 404792 (C4 (Web Text))

Max Activating Token Index: 673

Text #6

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.8820. Min Act: -0.0000

Data Index: 514062 (C4 (Web Text))

Max Activating Token Index: 902

Text #7

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.8027. Min Act: -0.0000

Data Index: 953047 (C4 (Web Text))

Max Activating Token Index: 671

Text #8

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.7406. Min Act: -0.0000

Data Index: 479431 (C4 (Web Text))

Max Activating Token Index: 686

Text #9

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.6635. Min Act: -0.0000

Data Index: 1325110 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.5229. Min Act: -0.0000

Data Index: 1302500 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.5164. Min Act: -0.0000

Data Index: 45903 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.5505. Min Act: -0.0000

Data Index: 372267 (C4 (Web Text))

Max Activating Token Index: 309

Text #13

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.4701. Min Act: -0.0000

Data Index: 1286501 (C4 (Web Text))

Max Activating Token Index: 125

Text #14

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.4847. Min Act: -0.0000

Data Index: 766881 (C4 (Web Text))

Max Activating Token Index: 489

Text #15

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.5184. Min Act: -0.0000

Data Index: 467440 (C4 (Web Text))

Max Activating Token Index: 170

Text #16

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.4237. Min Act: -0.0000

Data Index: 1283171 (C4 (Web Text))

Max Activating Token Index: 8

Text #17

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.5104. Min Act: -0.0000

Data Index: 1096297 (C4 (Web Text))

Max Activating Token Index: 342

Text #18

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.4944. Min Act: -0.0000

Data Index: 113279 (C4 (Web Text))

Max Activating Token Index: 200

Text #19

Max Range: 2.5156. Min Range: -2.5156

Max Act: 1.5521. Min Act: -0.0000

Data Index: 786775 (C4 (Web Text))

Max Activating Token Index: 966