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

Dataset: The Pile

Neuron 700 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.5879. Min Act: -0.0000

Data Index: 1927019 (The Pile)

Max Activating Token Index: 30

Text #1

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.6553. Min Act: -0.0000

Data Index: 1533765 (The Pile)

Max Activating Token Index: 298

Text #2

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.5960. Min Act: -0.0000

Data Index: 1477630 (The Pile)

Max Activating Token Index: 185

Text #3

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.8044. Min Act: -0.0001

Data Index: 606124 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.7634. Min Act: -0.0000

Data Index: 871024 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.6041. Min Act: -0.0000

Data Index: 1716525 (The Pile)

Max Activating Token Index: 424

Text #6

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.4681. Min Act: -0.0000

Data Index: 337000 (The Pile)

Max Activating Token Index: 534

Text #7

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.5175. Min Act: -0.0000

Data Index: 943875 (The Pile)

Max Activating Token Index: 88

Text #8

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.5375. Min Act: -0.0000

Data Index: 1560997 (The Pile)

Max Activating Token Index: 601

Text #9

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.5925. Min Act: -0.0000

Data Index: 1997455 (The Pile)

Max Activating Token Index: 129

Text #10

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3655. Min Act: -0.0000

Data Index: 533888 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.5471. Min Act: -0.0000

Data Index: 1289680 (The Pile)

Max Activating Token Index: 146

Text #12

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.0304. Min Act: -0.0000

Data Index: 1817127 (The Pile)

Max Activating Token Index: 813

Text #13

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.1659. Min Act: -0.0000

Data Index: 1523405 (The Pile)

Max Activating Token Index: 190

Text #14

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3399. Min Act: -0.0000

Data Index: 1273324 (The Pile)

Max Activating Token Index: 52

Text #15

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.4267. Min Act: -0.0000

Data Index: 1554602 (The Pile)

Max Activating Token Index: 465

Text #16

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3433. Min Act: -0.0000

Data Index: 774465 (The Pile)

Max Activating Token Index: 526

Text #17

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3301. Min Act: -0.0000

Data Index: 1427670 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.3572. Min Act: -0.0000

Data Index: 1572744 (The Pile)

Max Activating Token Index: 170

Text #19

Max Range: 1.8044. Min Range: -1.8044

Max Act: 1.2028. Min Act: -0.0000

Data Index: 1975974 (The Pile)

Max Activating Token Index: 792