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

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

Neuron 4548 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.6405. Min Act: -0.0000

Data Index: 853909 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.5001. Min Act: -0.0000

Data Index: 488466 (C4 (Web Text))

Max Activating Token Index: 998

Text #2

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4549. Min Act: -0.0000

Data Index: 394970 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4226. Min Act: -0.0000

Data Index: 86882 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4460. Min Act: -0.0000

Data Index: 596140 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1049554 (C4 (Web Text))

Max Activating Token Index: 370

Text #6

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.3558. Min Act: -0.0000

Data Index: 2006 (C4 (Web Text))

Max Activating Token Index: 542

Text #7

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.3339. Min Act: -0.0000

Data Index: 886915 (C4 (Web Text))

Max Activating Token Index: 378

Text #8

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1285083 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.3031. Min Act: -0.0000

Data Index: 171233 (C4 (Web Text))

Max Activating Token Index: 382

Text #10

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.3015. Min Act: -0.0000

Data Index: 854737 (C4 (Web Text))

Max Activating Token Index: 96

Text #11

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.3139. Min Act: -0.0000

Data Index: 1006145 (C4 (Web Text))

Max Activating Token Index: 167

Text #12

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.2586. Min Act: -0.0000

Data Index: 263921 (C4 (Web Text))

Max Activating Token Index: 733

Text #13

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.2866. Min Act: -0.0000

Data Index: 323603 (C4 (Web Text))

Max Activating Token Index: 85

Text #14

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.2971. Min Act: -0.0000

Data Index: 667417 (C4 (Web Text))

Max Activating Token Index: 958

Text #15

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.2353. Min Act: -0.0000

Data Index: 277942 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.2446. Min Act: -0.0000

Data Index: 1359705 (C4 (Web Text))

Max Activating Token Index: 630

Text #17

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.2279. Min Act: -0.0000

Data Index: 1096314 (C4 (Web Text))

Max Activating Token Index: 199

Text #18

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.2201. Min Act: -0.0000

Data Index: 534069 (C4 (Web Text))

Max Activating Token Index: 887

Text #19

Max Range: 0.6405. Min Range: -0.6405

Max Act: 0.2271. Min Act: -0.0000

Data Index: 279776 (C4 (Web Text))

Max Activating Token Index: 434