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

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

Neuron 5109 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6227. Min Act: -0.0001

Data Index: 1201015 (C4 (Web Text))

Max Activating Token Index: 317

Text #1

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8722. Min Act: -0.0001

Data Index: 1162874 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.3740. Min Act: -0.0001

Data Index: 718903 (C4 (Web Text))

Max Activating Token Index: 424

Text #3

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.8252. Min Act: -0.0001

Data Index: 1180888 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5654. Min Act: -0.0001

Data Index: 1038709 (C4 (Web Text))

Max Activating Token Index: 547

Text #5

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.2545. Min Act: -0.0001

Data Index: 601775 (C4 (Web Text))

Max Activating Token Index: 72

Text #6

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.4827. Min Act: -0.0001

Data Index: 107955 (C4 (Web Text))

Max Activating Token Index: 643

Text #7

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.2005. Min Act: -0.0001

Data Index: 758563 (C4 (Web Text))

Max Activating Token Index: 833

Text #8

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.5440. Min Act: -0.0001

Data Index: 486935 (C4 (Web Text))

Max Activating Token Index: 129

Text #9

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.6124. Min Act: -0.0001

Data Index: 934555 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.3674. Min Act: -0.0001

Data Index: 762137 (C4 (Web Text))

Max Activating Token Index: 13

Text #11

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.1379. Min Act: -0.0001

Data Index: 408342 (C4 (Web Text))

Max Activating Token Index: 662

Text #12

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.1523. Min Act: -0.0001

Data Index: 821455 (C4 (Web Text))

Max Activating Token Index: 261

Text #13

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.3782. Min Act: -0.0001

Data Index: 621862 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.3213. Min Act: -0.0001

Data Index: 934187 (C4 (Web Text))

Max Activating Token Index: 32

Text #15

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.3216. Min Act: -0.0001

Data Index: 1169932 (C4 (Web Text))

Max Activating Token Index: 990

Text #16

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.2339. Min Act: -0.0001

Data Index: 1090365 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.2780. Min Act: -0.0001

Data Index: 794347 (C4 (Web Text))

Max Activating Token Index: 601

Text #18

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.2835. Min Act: -0.0001

Data Index: 728383 (C4 (Web Text))

Max Activating Token Index: 1021

Text #19

Max Range: 1.8722. Min Range: -1.8722

Max Act: 1.2382. Min Act: -0.0001

Data Index: 926599 (C4 (Web Text))

Max Activating Token Index: 302