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

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

Neuron 3467 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3747. Min Range: -1.3747

Max Act: 1.3747. Min Act: -0.0000

Data Index: 538653 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.3747. Min Range: -1.3747

Max Act: 1.0519. Min Act: -0.0000

Data Index: 319713 (C4 (Web Text))

Max Activating Token Index: 191

Text #2

Max Range: 1.3747. Min Range: -1.3747

Max Act: 1.0153. Min Act: -0.0000

Data Index: 488295 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 1.3747. Min Range: -1.3747

Max Act: 1.0471. Min Act: -0.0000

Data Index: 299281 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9765. Min Act: -0.0000

Data Index: 676037 (C4 (Web Text))

Max Activating Token Index: 326

Text #5

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9394. Min Act: -0.0000

Data Index: 1261945 (C4 (Web Text))

Max Activating Token Index: 586

Text #6

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9510. Min Act: -0.0000

Data Index: 1095443 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9428. Min Act: -0.0000

Data Index: 153635 (C4 (Web Text))

Max Activating Token Index: 897

Text #8

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9478. Min Act: -0.0000

Data Index: 1085814 (C4 (Web Text))

Max Activating Token Index: 1022

Text #9

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9517. Min Act: -0.0000

Data Index: 690382 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9209. Min Act: -0.0000

Data Index: 926656 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1121139 (C4 (Web Text))

Max Activating Token Index: 953

Text #12

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9391. Min Act: -0.0000

Data Index: 988574 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9234. Min Act: -0.0000

Data Index: 484776 (C4 (Web Text))

Max Activating Token Index: 156

Text #14

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.8564. Min Act: -0.0000

Data Index: 1224903 (C4 (Web Text))

Max Activating Token Index: 653

Text #15

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9088. Min Act: -0.0000

Data Index: 725086 (C4 (Web Text))

Max Activating Token Index: 47

Text #16

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.8977. Min Act: -0.0000

Data Index: 395069 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.9257. Min Act: -0.0000

Data Index: 847875 (C4 (Web Text))

Max Activating Token Index: 709

Text #18

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.8648. Min Act: -0.0000

Data Index: 779222 (C4 (Web Text))

Max Activating Token Index: 434

Text #19

Max Range: 1.3747. Min Range: -1.3747

Max Act: 0.8347. Min Act: -0.0000

Data Index: 880225 (C4 (Web Text))

Max Activating Token Index: 956