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

Dataset: The Pile

Neuron 1959 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1060342 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1562951 (The Pile)

Max Activating Token Index: 959

Text #2

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.6144. Min Act: -0.0000

Data Index: 767421 (The Pile)

Max Activating Token Index: 539

Text #3

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.6211. Min Act: -0.0000

Data Index: 1382717 (The Pile)

Max Activating Token Index: 709

Text #4

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5520. Min Act: -0.0000

Data Index: 1008113 (The Pile)

Max Activating Token Index: 280

Text #5

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5496. Min Act: -0.0000

Data Index: 61165 (The Pile)

Max Activating Token Index: 290

Text #6

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5691. Min Act: -0.0000

Data Index: 1918560 (The Pile)

Max Activating Token Index: 893

Text #7

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1087808 (The Pile)

Max Activating Token Index: 572

Text #8

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5387. Min Act: -0.0000

Data Index: 820771 (The Pile)

Max Activating Token Index: 260

Text #9

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5351. Min Act: -0.0000

Data Index: 557091 (The Pile)

Max Activating Token Index: 425

Text #10

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5301. Min Act: -0.0000

Data Index: 1924460 (The Pile)

Max Activating Token Index: 312

Text #11

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5167. Min Act: -0.0000

Data Index: 1776465 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5162. Min Act: -0.0000

Data Index: 1034104 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.5379. Min Act: -0.0000

Data Index: 170279 (The Pile)

Max Activating Token Index: 1006

Text #14

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4881. Min Act: -0.0000

Data Index: 373104 (The Pile)

Max Activating Token Index: 467

Text #15

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4824. Min Act: -0.0000

Data Index: 23421 (The Pile)

Max Activating Token Index: 288

Text #16

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4664. Min Act: -0.0000

Data Index: 1714625 (The Pile)

Max Activating Token Index: 368

Text #17

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1571541 (The Pile)

Max Activating Token Index: 896

Text #18

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4719. Min Act: -0.0000

Data Index: 1447003 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 0.6211. Min Range: -0.6211

Max Act: 0.4741. Min Act: -0.0000

Data Index: 1697498 (The Pile)

Max Activating Token Index: 384