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

Dataset: The Pile

Neuron 445 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9964. Min Act: -0.0000

Data Index: 582032 (The Pile)

Max Activating Token Index: 1000

Text #1

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.9771. Min Act: -0.0000

Data Index: 518068 (The Pile)

Max Activating Token Index: 120

Text #2

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.8250. Min Act: -0.0000

Data Index: 700319 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7870. Min Act: -0.0000

Data Index: 75126 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7785. Min Act: -0.0000

Data Index: 190828 (The Pile)

Max Activating Token Index: 999

Text #5

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7536. Min Act: -0.0000

Data Index: 369977 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.7055. Min Act: -0.0000

Data Index: 1716504 (The Pile)

Max Activating Token Index: 515

Text #7

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6596. Min Act: -0.0000

Data Index: 229273 (The Pile)

Max Activating Token Index: 779

Text #8

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6966. Min Act: -0.0000

Data Index: 1617239 (The Pile)

Max Activating Token Index: 962

Text #9

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6582. Min Act: -0.0000

Data Index: 1364758 (The Pile)

Max Activating Token Index: 550

Text #10

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6690. Min Act: -0.0000

Data Index: 799647 (The Pile)

Max Activating Token Index: 383

Text #11

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6456. Min Act: -0.0000

Data Index: 854685 (The Pile)

Max Activating Token Index: 264

Text #12

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6031. Min Act: -0.0000

Data Index: 1995388 (The Pile)

Max Activating Token Index: 790

Text #13

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6510. Min Act: -0.0000

Data Index: 1895285 (The Pile)

Max Activating Token Index: 238

Text #14

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.5646. Min Act: -0.0000

Data Index: 1388343 (The Pile)

Max Activating Token Index: 743

Text #15

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.5899. Min Act: -0.0000

Data Index: 902644 (The Pile)

Max Activating Token Index: 699

Text #16

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.5744. Min Act: -0.0000

Data Index: 1365043 (The Pile)

Max Activating Token Index: 263

Text #17

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1791436 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1075732 (The Pile)

Max Activating Token Index: 400

Text #19

Max Range: 0.9964. Min Range: -0.9964

Max Act: 0.5742. Min Act: -0.0000

Data Index: 1949046 (The Pile)

Max Activating Token Index: 74