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

Dataset: The Pile

Neuron 1104 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: 1.5573. Min Range: -1.5573

Max Act: 1.5573. Min Act: -0.0000

Data Index: 1503356 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.3856. Min Act: -0.0000

Data Index: 66722 (The Pile)

Max Activating Token Index: 225

Text #2

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.4096. Min Act: -0.0000

Data Index: 1208258 (The Pile)

Max Activating Token Index: 453

Text #3

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.4065. Min Act: -0.0000

Data Index: 1288945 (The Pile)

Max Activating Token Index: 988

Text #4

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.4070. Min Act: -0.0000

Data Index: 1782041 (The Pile)

Max Activating Token Index: 533

Text #5

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.3547. Min Act: -0.0000

Data Index: 659873 (The Pile)

Max Activating Token Index: 291

Text #6

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.1916. Min Act: -0.0000

Data Index: 1288012 (The Pile)

Max Activating Token Index: 720

Text #7

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2536. Min Act: -0.0000

Data Index: 1671606 (The Pile)

Max Activating Token Index: 1002

Text #8

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.3318. Min Act: -0.0000

Data Index: 1977608 (The Pile)

Max Activating Token Index: 533

Text #9

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1219394 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.4716. Min Act: -0.0000

Data Index: 119127 (The Pile)

Max Activating Token Index: 651

Text #11

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2420. Min Act: -0.0000

Data Index: 144225 (The Pile)

Max Activating Token Index: 596

Text #12

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.3789. Min Act: -0.0000

Data Index: 1850227 (The Pile)

Max Activating Token Index: 823

Text #13

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.3027. Min Act: -0.0000

Data Index: 1936768 (The Pile)

Max Activating Token Index: 115

Text #14

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2071. Min Act: -0.0000

Data Index: 1333115 (The Pile)

Max Activating Token Index: 612

Text #15

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2258. Min Act: -0.0000

Data Index: 1685951 (The Pile)

Max Activating Token Index: 188

Text #16

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2874. Min Act: -0.0000

Data Index: 400021 (The Pile)

Max Activating Token Index: 30

Text #17

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2793. Min Act: -0.0000

Data Index: 925605 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2795. Min Act: -0.0000

Data Index: 1488944 (The Pile)

Max Activating Token Index: 802

Text #19

Max Range: 1.5573. Min Range: -1.5573

Max Act: 1.2555. Min Act: -0.0000

Data Index: 741383 (The Pile)

Max Activating Token Index: 979