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

Dataset: The Pile

Neuron 1082 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: 3.2712. Min Range: -3.2712

Max Act: 3.2712. Min Act: -0.0000

Data Index: 1725328 (The Pile)

Max Activating Token Index: 209

Text #1

Max Range: 3.2712. Min Range: -3.2712

Max Act: 3.1678. Min Act: -0.0000

Data Index: 1608303 (The Pile)

Max Activating Token Index: 288

Text #2

Max Range: 3.2712. Min Range: -3.2712

Max Act: 3.1942. Min Act: -0.0000

Data Index: 1237477 (The Pile)

Max Activating Token Index: 353

Text #3

Max Range: 3.2712. Min Range: -3.2712

Max Act: 2.9226. Min Act: -0.0000

Data Index: 191110 (The Pile)

Max Activating Token Index: 309

Text #4

Max Range: 3.2712. Min Range: -3.2712

Max Act: 2.1833. Min Act: -0.0000

Data Index: 513540 (The Pile)

Max Activating Token Index: 197

Text #5

Max Range: 3.2712. Min Range: -3.2712

Max Act: 2.0469. Min Act: -0.0000

Data Index: 946611 (The Pile)

Max Activating Token Index: 928

Text #6

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.9660. Min Act: -0.0000

Data Index: 1176526 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 3.2712. Min Range: -3.2712

Max Act: 2.0448. Min Act: -0.0000

Data Index: 898113 (The Pile)

Max Activating Token Index: 480

Text #8

Max Range: 3.2712. Min Range: -3.2712

Max Act: 2.1292. Min Act: -0.0000

Data Index: 889632 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 3.2712. Min Range: -3.2712

Max Act: 2.1203. Min Act: -0.0000

Data Index: 1390286 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.8195. Min Act: -0.0000

Data Index: 1880493 (The Pile)

Max Activating Token Index: 156

Text #11

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.7926. Min Act: -0.0000

Data Index: 770636 (The Pile)

Max Activating Token Index: 982

Text #12

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.7412. Min Act: -0.0000

Data Index: 1874514 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.8147. Min Act: -0.0000

Data Index: 1649023 (The Pile)

Max Activating Token Index: 694

Text #14

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.7119. Min Act: -0.0000

Data Index: 28207 (The Pile)

Max Activating Token Index: 179

Text #15

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.6440. Min Act: -0.0000

Data Index: 379457 (The Pile)

Max Activating Token Index: 196

Text #16

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.8444. Min Act: -0.0000

Data Index: 950352 (The Pile)

Max Activating Token Index: 59

Text #17

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.6994. Min Act: -0.0000

Data Index: 1665761 (The Pile)

Max Activating Token Index: 318

Text #18

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.6668. Min Act: -0.0000

Data Index: 1788102 (The Pile)

Max Activating Token Index: 1005

Text #19

Max Range: 3.2712. Min Range: -3.2712

Max Act: 1.6824. Min Act: -0.0000

Data Index: 675601 (The Pile)

Max Activating Token Index: 149