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

Dataset: The Pile

Neuron 3919 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: 1.3798. Min Range: -1.3798

Max Act: 1.3798. Min Act: -0.0000

Data Index: 1064040 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.3449. Min Act: -0.0000

Data Index: 301786 (The Pile)

Max Activating Token Index: 745

Text #2

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2999. Min Act: -0.0000

Data Index: 1412772 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.3290. Min Act: -0.0000

Data Index: 1935508 (The Pile)

Max Activating Token Index: 176

Text #4

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2839. Min Act: -0.0000

Data Index: 466739 (The Pile)

Max Activating Token Index: 294

Text #5

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2205. Min Act: -0.0000

Data Index: 435010 (The Pile)

Max Activating Token Index: 912

Text #6

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1711. Min Act: -0.0000

Data Index: 96594 (The Pile)

Max Activating Token Index: 993

Text #7

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2014. Min Act: -0.0000

Data Index: 956624 (The Pile)

Max Activating Token Index: 302

Text #8

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2011. Min Act: -0.0000

Data Index: 292081 (The Pile)

Max Activating Token Index: 801

Text #9

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2109. Min Act: -0.0000

Data Index: 1246623 (The Pile)

Max Activating Token Index: 937

Text #10

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1561. Min Act: -0.0000

Data Index: 963064 (The Pile)

Max Activating Token Index: 438

Text #11

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1954. Min Act: -0.0000

Data Index: 662741 (The Pile)

Max Activating Token Index: 813

Text #12

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1085. Min Act: -0.0000

Data Index: 597409 (The Pile)

Max Activating Token Index: 187

Text #13

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1382. Min Act: -0.0000

Data Index: 667171 (The Pile)

Max Activating Token Index: 455

Text #14

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.2069. Min Act: -0.0000

Data Index: 725165 (The Pile)

Max Activating Token Index: 260

Text #15

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1050. Min Act: -0.0000

Data Index: 659734 (The Pile)

Max Activating Token Index: 289

Text #16

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.1602. Min Act: -0.0000

Data Index: 751361 (The Pile)

Max Activating Token Index: 960

Text #17

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0742. Min Act: -0.0000

Data Index: 205150 (The Pile)

Max Activating Token Index: 121

Text #18

Max Range: 1.3798. Min Range: -1.3798

Max Act: 1.0945. Min Act: -0.0000

Data Index: 1887327 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 1.3798. Min Range: -1.3798

Max Act: 0.9921. Min Act: -0.0000

Data Index: 1774725 (The Pile)

Max Activating Token Index: 368