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

Dataset: The Pile

Neuron 61 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8816. Min Act: -0.0000

Data Index: 738324 (The Pile)

Max Activating Token Index: 261

Text #1

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.8416. Min Act: -0.0000

Data Index: 1334602 (The Pile)

Max Activating Token Index: 415

Text #2

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7541. Min Act: -0.0000

Data Index: 679521 (The Pile)

Max Activating Token Index: 708

Text #3

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7159. Min Act: -0.0000

Data Index: 1122566 (The Pile)

Max Activating Token Index: 74

Text #4

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6887. Min Act: -0.0000

Data Index: 95204 (The Pile)

Max Activating Token Index: 590

Text #5

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.7166. Min Act: -0.0000

Data Index: 188544 (The Pile)

Max Activating Token Index: 876

Text #6

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6654. Min Act: -0.0000

Data Index: 936835 (The Pile)

Max Activating Token Index: 973

Text #7

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6641. Min Act: -0.0000

Data Index: 320389 (The Pile)

Max Activating Token Index: 327

Text #8

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5925. Min Act: -0.0000

Data Index: 966268 (The Pile)

Max Activating Token Index: 113

Text #9

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5883. Min Act: -0.0000

Data Index: 1222041 (The Pile)

Max Activating Token Index: 599

Text #10

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6026. Min Act: -0.0000

Data Index: 381213 (The Pile)

Max Activating Token Index: 408

Text #11

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6357. Min Act: -0.0000

Data Index: 656480 (The Pile)

Max Activating Token Index: 41

Text #12

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5571. Min Act: -0.0000

Data Index: 538452 (The Pile)

Max Activating Token Index: 814

Text #13

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5890. Min Act: -0.0000

Data Index: 213409 (The Pile)

Max Activating Token Index: 156

Text #14

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6234. Min Act: -0.0000

Data Index: 1339688 (The Pile)

Max Activating Token Index: 639

Text #15

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.6443. Min Act: -0.0000

Data Index: 1717248 (The Pile)

Max Activating Token Index: 350

Text #16

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5834. Min Act: -0.0000

Data Index: 334573 (The Pile)

Max Activating Token Index: 905

Text #17

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5237. Min Act: -0.0000

Data Index: 1851259 (The Pile)

Max Activating Token Index: 622

Text #18

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5810. Min Act: -0.0000

Data Index: 18773 (The Pile)

Max Activating Token Index: 274

Text #19

Max Range: 0.8816. Min Range: -0.8816

Max Act: 0.5713. Min Act: -0.0000

Data Index: 1775414 (The Pile)

Max Activating Token Index: 876