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

Dataset: The Pile

Neuron 1701 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: 3.8041. Min Range: -3.8041

Max Act: 3.7659. Min Act: -0.0000

Data Index: 1626118 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.8041. Min Act: -0.0000

Data Index: 205392 (The Pile)

Max Activating Token Index: 297

Text #2

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.6496. Min Act: -0.0000

Data Index: 1562831 (The Pile)

Max Activating Token Index: 241

Text #3

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.4042. Min Act: -0.0000

Data Index: 1321806 (The Pile)

Max Activating Token Index: 377

Text #4

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.7629. Min Act: -0.0000

Data Index: 555569 (The Pile)

Max Activating Token Index: 160

Text #5

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.0426. Min Act: -0.0000

Data Index: 1262087 (The Pile)

Max Activating Token Index: 117

Text #6

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.1347. Min Act: -0.0000

Data Index: 427393 (The Pile)

Max Activating Token Index: 468

Text #7

Max Range: 3.8041. Min Range: -3.8041

Max Act: 2.9545. Min Act: -0.0000

Data Index: 122543 (The Pile)

Max Activating Token Index: 679

Text #8

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.0889. Min Act: -0.0000

Data Index: 1580246 (The Pile)

Max Activating Token Index: 186

Text #9

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.2224. Min Act: -0.0000

Data Index: 1102528 (The Pile)

Max Activating Token Index: 405

Text #10

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.2657. Min Act: -0.0000

Data Index: 701319 (The Pile)

Max Activating Token Index: 142

Text #11

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.1519. Min Act: -0.0000

Data Index: 575276 (The Pile)

Max Activating Token Index: 151

Text #12

Max Range: 3.8041. Min Range: -3.8041

Max Act: 2.6590. Min Act: -0.0000

Data Index: 1890044 (The Pile)

Max Activating Token Index: 420

Text #13

Max Range: 3.8041. Min Range: -3.8041

Max Act: 3.0789. Min Act: -0.0000

Data Index: 1617567 (The Pile)

Max Activating Token Index: 943

Text #14

Max Range: 3.8041. Min Range: -3.8041

Max Act: 2.7286. Min Act: -0.0000

Data Index: 1250429 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 3.8041. Min Range: -3.8041

Max Act: 2.5616. Min Act: -0.0000

Data Index: 925286 (The Pile)

Max Activating Token Index: 606

Text #16

Max Range: 3.8041. Min Range: -3.8041

Max Act: 2.5603. Min Act: -0.0000

Data Index: 585467 (The Pile)

Max Activating Token Index: 156

Text #17

Max Range: 3.8041. Min Range: -3.8041

Max Act: 2.8180. Min Act: -0.0000

Data Index: 1734026 (The Pile)

Max Activating Token Index: 68

Text #18

Max Range: 3.8041. Min Range: -3.8041

Max Act: 2.9368. Min Act: -0.0000

Data Index: 906865 (The Pile)

Max Activating Token Index: 157

Text #19

Max Range: 3.8041. Min Range: -3.8041

Max Act: 2.6439. Min Act: -0.0000

Data Index: 803927 (The Pile)

Max Activating Token Index: 152