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

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

Neuron 4580 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: 0.3406. Min Range: -0.3406

Max Act: 0.3372. Min Act: -0.0000

Data Index: 657211 (C4 (Web Text))

Max Activating Token Index: 31

Text #1

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.3406. Min Act: -0.0000

Data Index: 42011 (C4 (Web Text))

Max Activating Token Index: 233

Text #2

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.3209. Min Act: -0.0000

Data Index: 492828 (C4 (Web Text))

Max Activating Token Index: 123

Text #3

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.3180. Min Act: -0.0000

Data Index: 202840 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.3088. Min Act: -0.0000

Data Index: 459162 (C4 (Web Text))

Max Activating Token Index: 175

Text #5

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2926. Min Act: -0.0000

Data Index: 493062 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.3118. Min Act: -0.0000

Data Index: 115558 (C4 (Web Text))

Max Activating Token Index: 137

Text #7

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2978. Min Act: -0.0000

Data Index: 691566 (C4 (Web Text))

Max Activating Token Index: 821

Text #8

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1113376 (C4 (Web Text))

Max Activating Token Index: 560

Text #9

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2801. Min Act: -0.0000

Data Index: 100162 (C4 (Web Text))

Max Activating Token Index: 431

Text #10

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2950. Min Act: -0.0000

Data Index: 1019100 (C4 (Web Text))

Max Activating Token Index: 395

Text #11

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.3026. Min Act: -0.0000

Data Index: 676528 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2903. Min Act: -0.0000

Data Index: 963702 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.3006. Min Act: -0.0000

Data Index: 970704 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2942. Min Act: -0.0000

Data Index: 145809 (C4 (Web Text))

Max Activating Token Index: 353

Text #15

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2830. Min Act: -0.0000

Data Index: 821802 (C4 (Web Text))

Max Activating Token Index: 332

Text #16

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2660. Min Act: -0.0000

Data Index: 413556 (C4 (Web Text))

Max Activating Token Index: 790

Text #17

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2594. Min Act: -0.0000

Data Index: 594920 (C4 (Web Text))

Max Activating Token Index: 426

Text #18

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2766. Min Act: -0.0000

Data Index: 1048593 (C4 (Web Text))

Max Activating Token Index: 993

Text #19

Max Range: 0.3406. Min Range: -0.3406

Max Act: 0.2369. Min Act: -0.0000

Data Index: 843567 (C4 (Web Text))

Max Activating Token Index: 881