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

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

Neuron 1654 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: 0.6476. Min Range: -0.6476

Max Act: 0.6474. Min Act: -0.0000

Data Index: 848780 (C4 (Web Text))

Max Activating Token Index: 186

Text #1

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.6448. Min Act: -0.0000

Data Index: 555688 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.6398. Min Act: -0.0000

Data Index: 1316208 (C4 (Web Text))

Max Activating Token Index: 182

Text #3

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.6088. Min Act: -0.0000

Data Index: 983644 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.5940. Min Act: -0.0000

Data Index: 977487 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.6356. Min Act: -0.0000

Data Index: 749497 (C4 (Web Text))

Max Activating Token Index: 153

Text #6

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.6476. Min Act: -0.0000

Data Index: 1072233 (C4 (Web Text))

Max Activating Token Index: 639

Text #7

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.5763. Min Act: -0.0000

Data Index: 1102907 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.5792. Min Act: -0.0000

Data Index: 1041938 (C4 (Web Text))

Max Activating Token Index: 172

Text #9

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.5412. Min Act: -0.0000

Data Index: 724916 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.6096. Min Act: -0.0000

Data Index: 116378 (C4 (Web Text))

Max Activating Token Index: 479

Text #11

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.5710. Min Act: -0.0000

Data Index: 72253 (C4 (Web Text))

Max Activating Token Index: 689

Text #12

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.6120. Min Act: -0.0000

Data Index: 582431 (C4 (Web Text))

Max Activating Token Index: 679

Text #13

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1206280 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.5882. Min Act: -0.0000

Data Index: 856836 (C4 (Web Text))

Max Activating Token Index: 245

Text #15

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.5558. Min Act: -0.0000

Data Index: 516496 (C4 (Web Text))

Max Activating Token Index: 817

Text #16

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1226557 (C4 (Web Text))

Max Activating Token Index: 901

Text #17

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.4450. Min Act: -0.0000

Data Index: 1060674 (C4 (Web Text))

Max Activating Token Index: 460

Text #18

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.4452. Min Act: -0.0000

Data Index: 1224560 (C4 (Web Text))

Max Activating Token Index: 681

Text #19

Max Range: 0.6476. Min Range: -0.6476

Max Act: 0.4723. Min Act: -0.0000

Data Index: 603265 (C4 (Web Text))

Max Activating Token Index: 714