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

Dataset: The Pile

Neuron 3998 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: 1.3729. Min Range: -1.3729

Max Act: 1.3729. Min Act: -0.0000

Data Index: 947334 (The Pile)

Max Activating Token Index: 87

Text #1

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1554. Min Act: -0.0000

Data Index: 1120433 (The Pile)

Max Activating Token Index: 85

Text #2

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0856. Min Act: -0.0000

Data Index: 1378737 (The Pile)

Max Activating Token Index: 467

Text #3

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.1413. Min Act: -0.0000

Data Index: 673969 (The Pile)

Max Activating Token Index: 332

Text #4

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0964. Min Act: -0.0000

Data Index: 1093139 (The Pile)

Max Activating Token Index: 180

Text #5

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9742. Min Act: -0.0000

Data Index: 1174751 (The Pile)

Max Activating Token Index: 586

Text #6

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0332. Min Act: -0.0000

Data Index: 1322089 (The Pile)

Max Activating Token Index: 58

Text #7

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9392. Min Act: -0.0000

Data Index: 1759804 (The Pile)

Max Activating Token Index: 440

Text #8

Max Range: 1.3729. Min Range: -1.3729

Max Act: 1.0191. Min Act: -0.0000

Data Index: 895792 (The Pile)

Max Activating Token Index: 88

Text #9

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9414. Min Act: -0.0000

Data Index: 622757 (The Pile)

Max Activating Token Index: 706

Text #10

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9282. Min Act: -0.0000

Data Index: 896488 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9777. Min Act: -0.0000

Data Index: 1472932 (The Pile)

Max Activating Token Index: 307

Text #12

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9074. Min Act: -0.0000

Data Index: 869163 (The Pile)

Max Activating Token Index: 75

Text #13

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9395. Min Act: -0.0000

Data Index: 1413157 (The Pile)

Max Activating Token Index: 252

Text #14

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.8986. Min Act: -0.0000

Data Index: 540813 (The Pile)

Max Activating Token Index: 351

Text #15

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.8973. Min Act: -0.0000

Data Index: 1095253 (The Pile)

Max Activating Token Index: 418

Text #16

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.7870. Min Act: -0.0000

Data Index: 557540 (The Pile)

Max Activating Token Index: 589

Text #17

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.8594. Min Act: -0.0000

Data Index: 381712 (The Pile)

Max Activating Token Index: 234

Text #18

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.8122. Min Act: -0.0000

Data Index: 538156 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 1.3729. Min Range: -1.3729

Max Act: 0.9109. Min Act: -0.0000

Data Index: 512974 (The Pile)

Max Activating Token Index: 249