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

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

Neuron 688 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: 0.4880. Min Range: -0.4880

Max Act: 0.4880. Min Act: -0.0000

Data Index: 1009677 (C4 (Web Text))

Max Activating Token Index: 783

Text #1

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3934. Min Act: -0.0000

Data Index: 479575 (C4 (Web Text))

Max Activating Token Index: 553

Text #2

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.4004. Min Act: -0.0000

Data Index: 375835 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3967. Min Act: -0.0000

Data Index: 91640 (C4 (Web Text))

Max Activating Token Index: 351

Text #4

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1249619 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3493. Min Act: -0.0000

Data Index: 468694 (C4 (Web Text))

Max Activating Token Index: 931

Text #6

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3466. Min Act: -0.0000

Data Index: 982172 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3465. Min Act: -0.0000

Data Index: 1206868 (C4 (Web Text))

Max Activating Token Index: 852

Text #8

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3227. Min Act: -0.0000

Data Index: 524540 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3383. Min Act: -0.0000

Data Index: 948744 (C4 (Web Text))

Max Activating Token Index: 412

Text #10

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1047550 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3334. Min Act: -0.0000

Data Index: 987590 (C4 (Web Text))

Max Activating Token Index: 890

Text #12

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3248. Min Act: -0.0000

Data Index: 653792 (C4 (Web Text))

Max Activating Token Index: 177

Text #13

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3330. Min Act: -0.0000

Data Index: 386505 (C4 (Web Text))

Max Activating Token Index: 700

Text #14

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3254. Min Act: -0.0000

Data Index: 982517 (C4 (Web Text))

Max Activating Token Index: 931

Text #15

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3214. Min Act: -0.0000

Data Index: 166321 (C4 (Web Text))

Max Activating Token Index: 863

Text #16

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3007. Min Act: -0.0000

Data Index: 236324 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3090. Min Act: -0.0000

Data Index: 539495 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3042. Min Act: -0.0000

Data Index: 751096 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.4880. Min Range: -0.4880

Max Act: 0.3234. Min Act: -0.0000

Data Index: 961823 (C4 (Web Text))

Max Activating Token Index: 728