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

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

Neuron 4357 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0002

Data Index: 189684 (C4 (Web Text))

Max Activating Token Index: 64

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0581. Min Act: -0.0002

Data Index: 978803 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0574. Min Act: -0.0001

Data Index: 967337 (C4 (Web Text))

Max Activating Token Index: 118

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0560. Min Act: -0.0002

Data Index: 531874 (C4 (Web Text))

Max Activating Token Index: 158

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0548. Min Act: -0.0002

Data Index: 414524 (C4 (Web Text))

Max Activating Token Index: 15

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0516. Min Act: -0.0002

Data Index: 736013 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0528. Min Act: -0.0002

Data Index: 1078926 (C4 (Web Text))

Max Activating Token Index: 217

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0527. Min Act: -0.0002

Data Index: 3354 (C4 (Web Text))

Max Activating Token Index: 8

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0522. Min Act: -0.0002

Data Index: 43428 (C4 (Web Text))

Max Activating Token Index: 89

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0514. Min Act: -0.0002

Data Index: 319315 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0514. Min Act: -0.0002

Data Index: 390622 (C4 (Web Text))

Max Activating Token Index: 615

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0506. Min Act: -0.0002

Data Index: 1052841 (C4 (Web Text))

Max Activating Token Index: 494

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0503. Min Act: -0.0001

Data Index: 662342 (C4 (Web Text))

Max Activating Token Index: 85

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0499. Min Act: -0.0001

Data Index: 516505 (C4 (Web Text))

Max Activating Token Index: 328

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1062210 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0497. Min Act: -0.0002

Data Index: 1104347 (C4 (Web Text))

Max Activating Token Index: 231

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0474. Min Act: -0.0002

Data Index: 405366 (C4 (Web Text))

Max Activating Token Index: 840

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0489. Min Act: -0.0002

Data Index: 622497 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0485. Min Act: -0.0001

Data Index: 713542 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0479. Min Act: -0.0002

Data Index: 890506 (C4 (Web Text))

Max Activating Token Index: 181