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

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

Neuron 3474 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: 2.0394. Min Range: -2.0394

Max Act: 2.0394. Min Act: -0.0000

Data Index: 1100155 (C4 (Web Text))

Max Activating Token Index: 65

Text #1

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.9124. Min Act: -0.0000

Data Index: 689749 (C4 (Web Text))

Max Activating Token Index: 464

Text #2

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.8060. Min Act: -0.0000

Data Index: 258213 (C4 (Web Text))

Max Activating Token Index: 93

Text #3

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.8265. Min Act: -0.0000

Data Index: 767149 (C4 (Web Text))

Max Activating Token Index: 1002

Text #4

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.7198. Min Act: -0.0000

Data Index: 881578 (C4 (Web Text))

Max Activating Token Index: 250

Text #5

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.5203. Min Act: -0.0000

Data Index: 969790 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.6546. Min Act: -0.0000

Data Index: 1310680 (C4 (Web Text))

Max Activating Token Index: 424

Text #7

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.5978. Min Act: -0.0000

Data Index: 626294 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4789. Min Act: -0.0000

Data Index: 407673 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4926. Min Act: -0.0000

Data Index: 381891 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.5477. Min Act: -0.0000

Data Index: 851715 (C4 (Web Text))

Max Activating Token Index: 998

Text #11

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4873. Min Act: -0.0000

Data Index: 1290110 (C4 (Web Text))

Max Activating Token Index: 400

Text #12

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1305496 (C4 (Web Text))

Max Activating Token Index: 925

Text #13

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.5096. Min Act: -0.0000

Data Index: 630759 (C4 (Web Text))

Max Activating Token Index: 528

Text #14

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4111. Min Act: -0.0000

Data Index: 1086867 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4326. Min Act: -0.0000

Data Index: 1085407 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4406. Min Act: -0.0000

Data Index: 145723 (C4 (Web Text))

Max Activating Token Index: 940

Text #17

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4242. Min Act: -0.0000

Data Index: 177742 (C4 (Web Text))

Max Activating Token Index: 259

Text #18

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.4609. Min Act: -0.0000

Data Index: 1261608 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 2.0394. Min Range: -2.0394

Max Act: 1.3718. Min Act: -0.0000

Data Index: 968496 (C4 (Web Text))

Max Activating Token Index: 557