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

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

Neuron 938 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0073. Min Range: -2.0073

Max Act: 2.0073. Min Act: -0.0000

Data Index: 658306 (C4 (Web Text))

Max Activating Token Index: 426

Text #1

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.7437. Min Act: -0.0000

Data Index: 206705 (C4 (Web Text))

Max Activating Token Index: 899

Text #2

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.6322. Min Act: -0.0000

Data Index: 393387 (C4 (Web Text))

Max Activating Token Index: 906

Text #3

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.7130. Min Act: -0.0000

Data Index: 933788 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.6739. Min Act: -0.0000

Data Index: 309150 (C4 (Web Text))

Max Activating Token Index: 269

Text #5

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.6733. Min Act: -0.0000

Data Index: 536881 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.6143. Min Act: -0.0000

Data Index: 320743 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.4954. Min Act: -0.0000

Data Index: 840500 (C4 (Web Text))

Max Activating Token Index: 645

Text #8

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.4607. Min Act: -0.0000

Data Index: 260152 (C4 (Web Text))

Max Activating Token Index: 150

Text #9

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.4540. Min Act: -0.0000

Data Index: 827115 (C4 (Web Text))

Max Activating Token Index: 426

Text #10

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.4223. Min Act: -0.0000

Data Index: 561020 (C4 (Web Text))

Max Activating Token Index: 636

Text #11

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.4210. Min Act: -0.0000

Data Index: 838425 (C4 (Web Text))

Max Activating Token Index: 451

Text #12

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.3778. Min Act: -0.0000

Data Index: 995013 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.3695. Min Act: -0.0000

Data Index: 940511 (C4 (Web Text))

Max Activating Token Index: 352

Text #14

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.3507. Min Act: -0.0000

Data Index: 997809 (C4 (Web Text))

Max Activating Token Index: 358

Text #15

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.2552. Min Act: -0.0000

Data Index: 876501 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.3190. Min Act: -0.0000

Data Index: 834373 (C4 (Web Text))

Max Activating Token Index: 266

Text #17

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.2164. Min Act: -0.0000

Data Index: 1166804 (C4 (Web Text))

Max Activating Token Index: 281

Text #18

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.2931. Min Act: -0.0000

Data Index: 774779 (C4 (Web Text))

Max Activating Token Index: 354

Text #19

Max Range: 2.0073. Min Range: -2.0073

Max Act: 1.2152. Min Act: -0.0000

Data Index: 348501 (C4 (Web Text))

Max Activating Token Index: 172