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

Dataset: The Pile

Neuron 3964 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: 0.6723. Min Range: -0.6723

Max Act: 0.6723. Min Act: -0.0000

Data Index: 1993494 (The Pile)

Max Activating Token Index: 1002

Text #1

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6426. Min Act: -0.0000

Data Index: 839742 (The Pile)

Max Activating Token Index: 78

Text #2

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6304. Min Act: -0.0000

Data Index: 189892 (The Pile)

Max Activating Token Index: 583

Text #3

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6069. Min Act: -0.0000

Data Index: 874987 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5933. Min Act: -0.0000

Data Index: 480336 (The Pile)

Max Activating Token Index: 728

Text #5

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5894. Min Act: -0.0000

Data Index: 1097811 (The Pile)

Max Activating Token Index: 670

Text #6

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5483. Min Act: -0.0000

Data Index: 613272 (The Pile)

Max Activating Token Index: 306

Text #7

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.6153. Min Act: -0.0000

Data Index: 1313960 (The Pile)

Max Activating Token Index: 1022

Text #8

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5459. Min Act: -0.0000

Data Index: 607968 (The Pile)

Max Activating Token Index: 568

Text #9

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5627. Min Act: -0.0000

Data Index: 295907 (The Pile)

Max Activating Token Index: 341

Text #10

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5406. Min Act: -0.0000

Data Index: 493160 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5539. Min Act: -0.0000

Data Index: 1130833 (The Pile)

Max Activating Token Index: 93

Text #12

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5601. Min Act: -0.0000

Data Index: 1674182 (The Pile)

Max Activating Token Index: 105

Text #13

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5280. Min Act: -0.0000

Data Index: 1245706 (The Pile)

Max Activating Token Index: 361

Text #14

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5227. Min Act: -0.0000

Data Index: 1786179 (The Pile)

Max Activating Token Index: 767

Text #15

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5164. Min Act: -0.0000

Data Index: 1743371 (The Pile)

Max Activating Token Index: 376

Text #16

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5328. Min Act: -0.0000

Data Index: 1209816 (The Pile)

Max Activating Token Index: 397

Text #17

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5054. Min Act: -0.0000

Data Index: 648704 (The Pile)

Max Activating Token Index: 626

Text #18

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1452982 (The Pile)

Max Activating Token Index: 643

Text #19

Max Range: 0.6723. Min Range: -0.6723

Max Act: 0.4831. Min Act: -0.0000

Data Index: 117088 (The Pile)

Max Activating Token Index: 429