Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1936 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5804. Min Act: -0.0000

Data Index: 1698037 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5526. Min Act: -0.0000

Data Index: 740319 (The Pile)

Max Activating Token Index: 764

Text #2

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5587. Min Act: -0.0000

Data Index: 1123304 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5446. Min Act: -0.0000

Data Index: 1028675 (The Pile)

Max Activating Token Index: 214

Text #4

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5350. Min Act: -0.0000

Data Index: 420845 (The Pile)

Max Activating Token Index: 345

Text #5

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5062. Min Act: -0.0000

Data Index: 724938 (The Pile)

Max Activating Token Index: 665

Text #6

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5533. Min Act: -0.0000

Data Index: 1059279 (The Pile)

Max Activating Token Index: 528

Text #7

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1095262 (The Pile)

Max Activating Token Index: 76

Text #8

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.5334. Min Act: -0.0000

Data Index: 1050430 (The Pile)

Max Activating Token Index: 299

Text #9

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4625. Min Act: -0.0000

Data Index: 499368 (The Pile)

Max Activating Token Index: 584

Text #10

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1544842 (The Pile)

Max Activating Token Index: 658

Text #11

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4634. Min Act: -0.0000

Data Index: 219398 (The Pile)

Max Activating Token Index: 859

Text #12

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4587. Min Act: -0.0000

Data Index: 1042722 (The Pile)

Max Activating Token Index: 253

Text #13

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4286. Min Act: -0.0000

Data Index: 865662 (The Pile)

Max Activating Token Index: 632

Text #14

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4576. Min Act: -0.0000

Data Index: 1630066 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4602. Min Act: -0.0000

Data Index: 290147 (The Pile)

Max Activating Token Index: 298

Text #16

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4330. Min Act: -0.0000

Data Index: 1963829 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4373. Min Act: -0.0000

Data Index: 1383798 (The Pile)

Max Activating Token Index: 860

Text #18

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4589. Min Act: -0.0000

Data Index: 1458639 (The Pile)

Max Activating Token Index: 33

Text #19

Max Range: 0.5804. Min Range: -0.5804

Max Act: 0.4332. Min Act: -0.0000

Data Index: 462817 (The Pile)

Max Activating Token Index: 741