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

Dataset: The Pile

Neuron 861 in Layer 7

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: 1512027 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8357. Min Act: -0.0000

Data Index: 202360 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.8079. Min Act: -0.0000

Data Index: 884812 (The Pile)

Max Activating Token Index: 145

Text #3

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.7523. Min Act: -0.0000

Data Index: 315728 (The Pile)

Max Activating Token Index: 118

Text #4

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6802. Min Act: -0.0000

Data Index: 1726271 (The Pile)

Max Activating Token Index: 348

Text #5

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6978. Min Act: -0.0000

Data Index: 213941 (The Pile)

Max Activating Token Index: 525

Text #6

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6837. Min Act: -0.0000

Data Index: 1422792 (The Pile)

Max Activating Token Index: 662

Text #7

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1454980 (The Pile)

Max Activating Token Index: 678

Text #8

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6694. Min Act: -0.0000

Data Index: 431314 (The Pile)

Max Activating Token Index: 966

Text #9

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6538. Min Act: -0.0000

Data Index: 182446 (The Pile)

Max Activating Token Index: 102

Text #10

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.5981. Min Act: -0.0000

Data Index: 1025804 (The Pile)

Max Activating Token Index: 433

Text #11

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1471552 (The Pile)

Max Activating Token Index: 730

Text #12

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.5854. Min Act: -0.0000

Data Index: 646068 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1882357 (The Pile)

Max Activating Token Index: 819

Text #14

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6397. Min Act: -0.0000

Data Index: 195690 (The Pile)

Max Activating Token Index: 188

Text #15

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6404. Min Act: -0.0000

Data Index: 1547035 (The Pile)

Max Activating Token Index: 596

Text #16

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1169708 (The Pile)

Max Activating Token Index: 547

Text #17

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6312. Min Act: -0.0000

Data Index: 706143 (The Pile)

Max Activating Token Index: 390

Text #18

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6573. Min Act: -0.0000

Data Index: 337425 (The Pile)

Max Activating Token Index: 179

Text #19

Max Range: 0.9723. Min Range: -0.9723

Max Act: 0.6310. Min Act: -0.0000

Data Index: 576546 (The Pile)

Max Activating Token Index: 493