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

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

Neuron 3199 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.2601. Min Act: -0.0001

Data Index: 446184 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.1532. Min Act: -0.0001

Data Index: 641696 (C4 (Web Text))

Max Activating Token Index: 148

Text #2

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.1275. Min Act: -0.0001

Data Index: 1344917 (C4 (Web Text))

Max Activating Token Index: 94

Text #3

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.0979. Min Act: -0.0001

Data Index: 1208531 (C4 (Web Text))

Max Activating Token Index: 553

Text #4

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.0697. Min Act: -0.0001

Data Index: 354402 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9084. Min Act: -0.0001

Data Index: 1027175 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.1018. Min Act: -0.0001

Data Index: 752508 (C4 (Web Text))

Max Activating Token Index: 332

Text #7

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.3111. Min Act: -0.0001

Data Index: 1025406 (C4 (Web Text))

Max Activating Token Index: 236

Text #8

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.1682. Min Act: -0.0001

Data Index: 197218 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.0071. Min Act: -0.0001

Data Index: 113128 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.1932. Min Act: -0.0001

Data Index: 538396 (C4 (Web Text))

Max Activating Token Index: 551

Text #11

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.2618. Min Act: -0.0001

Data Index: 491940 (C4 (Web Text))

Max Activating Token Index: 504

Text #12

Max Range: 1.3111. Min Range: -1.3111

Max Act: 1.0528. Min Act: -0.0001

Data Index: 1241305 (C4 (Web Text))

Max Activating Token Index: 380

Text #13

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9358. Min Act: -0.0001

Data Index: 1183162 (C4 (Web Text))

Max Activating Token Index: 307

Text #14

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.7901. Min Act: -0.0001

Data Index: 1125552 (C4 (Web Text))

Max Activating Token Index: 619

Text #15

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9974. Min Act: -0.0001

Data Index: 311483 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9601. Min Act: -0.0001

Data Index: 72573 (C4 (Web Text))

Max Activating Token Index: 844

Text #17

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9644. Min Act: -0.0001

Data Index: 653783 (C4 (Web Text))

Max Activating Token Index: 587

Text #18

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9573. Min Act: -0.0001

Data Index: 651574 (C4 (Web Text))

Max Activating Token Index: 901

Text #19

Max Range: 1.3111. Min Range: -1.3111

Max Act: 0.9486. Min Act: -0.0001

Data Index: 716519 (C4 (Web Text))

Max Activating Token Index: 75