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

Dataset: The Pile

Neuron 69 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.7040. Min Act: -0.0000

Data Index: 1955144 (The Pile)

Max Activating Token Index: 646

Text #1

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6373. Min Act: -0.0000

Data Index: 1976889 (The Pile)

Max Activating Token Index: 745

Text #2

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5770. Min Act: -0.0000

Data Index: 866540 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.6285. Min Act: -0.0000

Data Index: 1580658 (The Pile)

Max Activating Token Index: 651

Text #4

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5753. Min Act: -0.0000

Data Index: 946884 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5749. Min Act: -0.0000

Data Index: 1345758 (The Pile)

Max Activating Token Index: 83

Text #6

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5801. Min Act: -0.0000

Data Index: 1407090 (The Pile)

Max Activating Token Index: 118

Text #7

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1354142 (The Pile)

Max Activating Token Index: 236

Text #8

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5534. Min Act: -0.0000

Data Index: 1816162 (The Pile)

Max Activating Token Index: 345

Text #9

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5833. Min Act: -0.0000

Data Index: 262409 (The Pile)

Max Activating Token Index: 661

Text #10

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5651. Min Act: -0.0000

Data Index: 641112 (The Pile)

Max Activating Token Index: 657

Text #11

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5610. Min Act: -0.0000

Data Index: 1736695 (The Pile)

Max Activating Token Index: 235

Text #12

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1645760 (The Pile)

Max Activating Token Index: 627

Text #13

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.4826. Min Act: -0.0000

Data Index: 797541 (The Pile)

Max Activating Token Index: 913

Text #14

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5177. Min Act: -0.0000

Data Index: 1536381 (The Pile)

Max Activating Token Index: 261

Text #15

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5041. Min Act: -0.0000

Data Index: 1231688 (The Pile)

Max Activating Token Index: 83

Text #16

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.4554. Min Act: -0.0000

Data Index: 1477120 (The Pile)

Max Activating Token Index: 551

Text #17

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.5288. Min Act: -0.0000

Data Index: 10711 (The Pile)

Max Activating Token Index: 44

Text #18

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.4923. Min Act: -0.0000

Data Index: 684365 (The Pile)

Max Activating Token Index: 890

Text #19

Max Range: 0.7040. Min Range: -0.7040

Max Act: 0.4901. Min Act: -0.0000

Data Index: 1304225 (The Pile)

Max Activating Token Index: 94