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

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

Neuron 1342 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0557. Min Act: -0.0002

Data Index: 781500 (C4 (Web Text))

Max Activating Token Index: 877

Text #1

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0470. Min Act: -0.0002

Data Index: 572191 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0415. Min Act: -0.0002

Data Index: 244651 (C4 (Web Text))

Max Activating Token Index: 162

Text #3

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0488. Min Act: -0.0002

Data Index: 1060564 (C4 (Web Text))

Max Activating Token Index: 130

Text #4

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0458. Min Act: -0.0002

Data Index: 502848 (C4 (Web Text))

Max Activating Token Index: 22

Text #5

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0463. Min Act: -0.0002

Data Index: 1126089 (C4 (Web Text))

Max Activating Token Index: 113

Text #6

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0447. Min Act: -0.0002

Data Index: 624295 (C4 (Web Text))

Max Activating Token Index: 594

Text #7

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0469. Min Act: -0.0002

Data Index: 772013 (C4 (Web Text))

Max Activating Token Index: 216

Text #8

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0424. Min Act: -0.0002

Data Index: 48037 (C4 (Web Text))

Max Activating Token Index: 336

Text #9

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0388. Min Act: -0.0002

Data Index: 173764 (C4 (Web Text))

Max Activating Token Index: 319

Text #10

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0425. Min Act: -0.0002

Data Index: 997481 (C4 (Web Text))

Max Activating Token Index: 730

Text #11

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0430. Min Act: -0.0002

Data Index: 1286964 (C4 (Web Text))

Max Activating Token Index: 480

Text #12

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0391. Min Act: -0.0002

Data Index: 826286 (C4 (Web Text))

Max Activating Token Index: 545

Text #13

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0383. Min Act: -0.0002

Data Index: 885447 (C4 (Web Text))

Max Activating Token Index: 493

Text #14

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0413. Min Act: -0.0002

Data Index: 849239 (C4 (Web Text))

Max Activating Token Index: 343

Text #15

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0420. Min Act: -0.0002

Data Index: 1149752 (C4 (Web Text))

Max Activating Token Index: 362

Text #16

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0378. Min Act: -0.0002

Data Index: 356972 (C4 (Web Text))

Max Activating Token Index: 801

Text #17

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0402. Min Act: -0.0002

Data Index: 1297769 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0424. Min Act: -0.0002

Data Index: 165963 (C4 (Web Text))

Max Activating Token Index: 999

Text #19

Max Range: 0.0557. Min Range: -0.0557

Max Act: 0.0376. Min Act: -0.0002

Data Index: 122894 (C4 (Web Text))

Max Activating Token Index: 852