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

Dataset: The Pile

Neuron 1068 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: 0.5080. Min Range: -0.5080

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1723788 (The Pile)

Max Activating Token Index: 281

Text #1

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3832. Min Act: -0.0000

Data Index: 541163 (The Pile)

Max Activating Token Index: 236

Text #2

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4038. Min Act: -0.0000

Data Index: 1414461 (The Pile)

Max Activating Token Index: 424

Text #3

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3933. Min Act: -0.0000

Data Index: 136519 (The Pile)

Max Activating Token Index: 535

Text #4

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.4126. Min Act: -0.0000

Data Index: 1405991 (The Pile)

Max Activating Token Index: 431

Text #5

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3541. Min Act: -0.0000

Data Index: 761030 (The Pile)

Max Activating Token Index: 161

Text #6

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3653. Min Act: -0.0000

Data Index: 47368 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3287. Min Act: -0.0000

Data Index: 415795 (The Pile)

Max Activating Token Index: 693

Text #8

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3631. Min Act: -0.0000

Data Index: 702845 (The Pile)

Max Activating Token Index: 202

Text #9

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3365. Min Act: -0.0000

Data Index: 1970041 (The Pile)

Max Activating Token Index: 317

Text #10

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3451. Min Act: -0.0000

Data Index: 737703 (The Pile)

Max Activating Token Index: 411

Text #11

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3451. Min Act: -0.0000

Data Index: 1932475 (The Pile)

Max Activating Token Index: 887

Text #12

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1974218 (The Pile)

Max Activating Token Index: 610

Text #13

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3115. Min Act: -0.0000

Data Index: 1450381 (The Pile)

Max Activating Token Index: 835

Text #14

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3264. Min Act: -0.0000

Data Index: 1556544 (The Pile)

Max Activating Token Index: 496

Text #15

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3163. Min Act: -0.0000

Data Index: 1464923 (The Pile)

Max Activating Token Index: 310

Text #16

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3359. Min Act: -0.0000

Data Index: 181069 (The Pile)

Max Activating Token Index: 447

Text #17

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3064. Min Act: -0.0000

Data Index: 446909 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3135. Min Act: -0.0000

Data Index: 1234170 (The Pile)

Max Activating Token Index: 681

Text #19

Max Range: 0.5080. Min Range: -0.5080

Max Act: 0.3153. Min Act: -0.0000

Data Index: 1061569 (The Pile)

Max Activating Token Index: 198