Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2974 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6738. Min Act: -0.0001

Data Index: 263791 (C4 (Web Text))

Max Activating Token Index: 150

Text #1

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.6157. Min Act: -0.0001

Data Index: 611714 (C4 (Web Text))

Max Activating Token Index: 369

Text #2

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5880. Min Act: -0.0000

Data Index: 429479 (C4 (Web Text))

Max Activating Token Index: 20

Text #3

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5625. Min Act: -0.0001

Data Index: 579006 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5745. Min Act: -0.0001

Data Index: 1018792 (C4 (Web Text))

Max Activating Token Index: 590

Text #5

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5803. Min Act: -0.0001

Data Index: 1341800 (C4 (Web Text))

Max Activating Token Index: 819

Text #6

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5583. Min Act: -0.0001

Data Index: 522663 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5760. Min Act: -0.0001

Data Index: 336787 (C4 (Web Text))

Max Activating Token Index: 714

Text #8

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5683. Min Act: -0.0000

Data Index: 1115228 (C4 (Web Text))

Max Activating Token Index: 834

Text #9

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5741. Min Act: -0.0001

Data Index: 773692 (C4 (Web Text))

Max Activating Token Index: 863

Text #10

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5298. Min Act: -0.0000

Data Index: 772671 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5437. Min Act: -0.0000

Data Index: 250915 (C4 (Web Text))

Max Activating Token Index: 12

Text #12

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5397. Min Act: -0.0001

Data Index: 278691 (C4 (Web Text))

Max Activating Token Index: 75

Text #13

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5183. Min Act: -0.0000

Data Index: 1326536 (C4 (Web Text))

Max Activating Token Index: 175

Text #14

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5517. Min Act: -0.0001

Data Index: 273767 (C4 (Web Text))

Max Activating Token Index: 149

Text #15

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5586. Min Act: -0.0000

Data Index: 282159 (C4 (Web Text))

Max Activating Token Index: 359

Text #16

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5038. Min Act: -0.0000

Data Index: 344328 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5038. Min Act: -0.0001

Data Index: 288988 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5346. Min Act: -0.0000

Data Index: 1131214 (C4 (Web Text))

Max Activating Token Index: 229

Text #19

Max Range: 0.6738. Min Range: -0.6738

Max Act: 0.5191. Min Act: -0.0000

Data Index: 761408 (C4 (Web Text))

Max Activating Token Index: 1002