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

Dataset: The Pile

Neuron 98 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: 0.9723. Min Range: -0.9723

Max Act: 0.9723. Min Act: -0.0000

Data Index: 818190 (The Pile)

Max Activating Token Index: 669

Text #1

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.9233. Min Act: 0.0000

Data Index: 1870660 (The Pile)

Max Activating Token Index: 429

Text #2

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8999. Min Act: -0.0000

Data Index: 890939 (The Pile)

Max Activating Token Index: 752

Text #3

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.9496. Min Act: -0.0000

Data Index: 53264 (The Pile)

Max Activating Token Index: 538

Text #4

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.9375. Min Act: -0.0000

Data Index: 32190 (The Pile)

Max Activating Token Index: 289

Text #5

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.9091. Min Act: -0.0000

Data Index: 1581650 (The Pile)

Max Activating Token Index: 721

Text #6

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8561. Min Act: -0.0000

Data Index: 721257 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8563. Min Act: 0.0000

Data Index: 1079299 (The Pile)

Max Activating Token Index: 441

Text #8

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7836. Min Act: -0.0000

Data Index: 565360 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8124. Min Act: -0.0000

Data Index: 1186069 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8475. Min Act: 0.0000

Data Index: 485288 (The Pile)

Max Activating Token Index: 327

Text #11

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7941. Min Act: -0.0000

Data Index: 811999 (The Pile)

Max Activating Token Index: 97

Text #12

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7808. Min Act: -0.0000

Data Index: 108800 (The Pile)

Max Activating Token Index: 926

Text #13

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7709. Min Act: -0.0000

Data Index: 1815335 (The Pile)

Max Activating Token Index: 231

Text #14

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8126. Min Act: -0.0000

Data Index: 1029543 (The Pile)

Max Activating Token Index: 365

Text #15

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7650. Min Act: -0.0000

Data Index: 338792 (The Pile)

Max Activating Token Index: 195

Text #16

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7941. Min Act: -0.0000

Data Index: 840821 (The Pile)

Max Activating Token Index: 810

Text #17

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7757. Min Act: 0.0000

Data Index: 102572 (The Pile)

Max Activating Token Index: 802

Text #18

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8292. Min Act: -0.0000

Data Index: 45442 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7953. Min Act: -0.0000

Data Index: 794362 (The Pile)

Max Activating Token Index: 220