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

Dataset: The Pile

Neuron 3449 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: 3.8115. Min Range: -3.8115

Max Act: 3.6161. Min Act: -0.0000

Data Index: 238600 (The Pile)

Max Activating Token Index: 483

Text #1

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.6771. Min Act: -0.0000

Data Index: 267405 (The Pile)

Max Activating Token Index: 411

Text #2

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.2823. Min Act: -0.0000

Data Index: 897017 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.5087. Min Act: -0.0000

Data Index: 1307975 (The Pile)

Max Activating Token Index: 735

Text #4

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.5842. Min Act: -0.0000

Data Index: 1971178 (The Pile)

Max Activating Token Index: 543

Text #5

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.8115. Min Act: -0.0000

Data Index: 380919 (The Pile)

Max Activating Token Index: 771

Text #6

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.7327. Min Act: -0.0000

Data Index: 1189606 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.6182. Min Act: -0.0000

Data Index: 271476 (The Pile)

Max Activating Token Index: 788

Text #8

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.4087. Min Act: -0.0000

Data Index: 1902580 (The Pile)

Max Activating Token Index: 979

Text #9

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.6816. Min Act: -0.0000

Data Index: 111625 (The Pile)

Max Activating Token Index: 927

Text #10

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.6768. Min Act: -0.0000

Data Index: 1400560 (The Pile)

Max Activating Token Index: 646

Text #11

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.4292. Min Act: -0.0000

Data Index: 1966488 (The Pile)

Max Activating Token Index: 131

Text #12

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.4983. Min Act: -0.0000

Data Index: 1767876 (The Pile)

Max Activating Token Index: 910

Text #13

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.1272. Min Act: -0.0000

Data Index: 1156831 (The Pile)

Max Activating Token Index: 525

Text #14

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.4925. Min Act: -0.0000

Data Index: 1943997 (The Pile)

Max Activating Token Index: 240

Text #15

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.3052. Min Act: -0.0000

Data Index: 1917571 (The Pile)

Max Activating Token Index: 680

Text #16

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.0000. Min Act: -0.0000

Data Index: 1909665 (The Pile)

Max Activating Token Index: 789

Text #17

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.3258. Min Act: -0.0000

Data Index: 1268903 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 3.8115. Min Range: -3.8115

Max Act: 2.9888. Min Act: -0.0000

Data Index: 1233492 (The Pile)

Max Activating Token Index: 483

Text #19

Max Range: 3.8115. Min Range: -3.8115

Max Act: 3.6417. Min Act: -0.0000

Data Index: 1596945 (The Pile)

Max Activating Token Index: 182