Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2626 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.3154. Min Act: -0.0001

Data Index: 1271369 (C4 (Web Text))

Max Activating Token Index: 978

Text #1

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2875. Min Act: -0.0001

Data Index: 868237 (C4 (Web Text))

Max Activating Token Index: 808

Text #2

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2773. Min Act: -0.0001

Data Index: 541130 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2808. Min Act: -0.0000

Data Index: 334772 (C4 (Web Text))

Max Activating Token Index: 302

Text #4

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1212037 (C4 (Web Text))

Max Activating Token Index: 548

Text #5

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2642. Min Act: -0.0001

Data Index: 143063 (C4 (Web Text))

Max Activating Token Index: 907

Text #6

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2661. Min Act: -0.0001

Data Index: 344135 (C4 (Web Text))

Max Activating Token Index: 437

Text #7

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2653. Min Act: -0.0000

Data Index: 795547 (C4 (Web Text))

Max Activating Token Index: 900

Text #8

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2678. Min Act: -0.0000

Data Index: 868440 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2458. Min Act: -0.0000

Data Index: 316274 (C4 (Web Text))

Max Activating Token Index: 305

Text #10

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2499. Min Act: -0.0001

Data Index: 70321 (C4 (Web Text))

Max Activating Token Index: 923

Text #11

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2527. Min Act: -0.0001

Data Index: 963021 (C4 (Web Text))

Max Activating Token Index: 913

Text #12

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2344. Min Act: -0.0001

Data Index: 1338185 (C4 (Web Text))

Max Activating Token Index: 245

Text #13

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2398. Min Act: -0.0000

Data Index: 1215259 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2385. Min Act: -0.0001

Data Index: 418335 (C4 (Web Text))

Max Activating Token Index: 30

Text #15

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2364. Min Act: -0.0001

Data Index: 1034362 (C4 (Web Text))

Max Activating Token Index: 350

Text #16

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2347. Min Act: -0.0001

Data Index: 922379 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2363. Min Act: -0.0001

Data Index: 471146 (C4 (Web Text))

Max Activating Token Index: 568

Text #18

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2362. Min Act: -0.0001

Data Index: 1183923 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.3154. Min Range: -0.3154

Max Act: 0.2265. Min Act: -0.0001

Data Index: 1150025 (C4 (Web Text))

Max Activating Token Index: 125