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

Dataset: The Pile

Neuron 1769 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: 0.4874. Min Range: -0.4874

Max Act: 0.4857. Min Act: -0.0000

Data Index: 1155454 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4874. Min Act: -0.0000

Data Index: 850511 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4588. Min Act: -0.0000

Data Index: 783381 (The Pile)

Max Activating Token Index: 527

Text #3

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4713. Min Act: -0.0000

Data Index: 927854 (The Pile)

Max Activating Token Index: 323

Text #4

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4275. Min Act: -0.0000

Data Index: 1825365 (The Pile)

Max Activating Token Index: 797

Text #5

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4411. Min Act: -0.0000

Data Index: 238286 (The Pile)

Max Activating Token Index: 902

Text #6

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4446. Min Act: -0.0000

Data Index: 615718 (The Pile)

Max Activating Token Index: 996

Text #7

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4310. Min Act: -0.0000

Data Index: 1973056 (The Pile)

Max Activating Token Index: 25

Text #8

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4370. Min Act: -0.0000

Data Index: 1679075 (The Pile)

Max Activating Token Index: 381

Text #9

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4374. Min Act: -0.0000

Data Index: 473520 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4350. Min Act: -0.0000

Data Index: 879370 (The Pile)

Max Activating Token Index: 126

Text #11

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4353. Min Act: -0.0000

Data Index: 659977 (The Pile)

Max Activating Token Index: 393

Text #12

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4156. Min Act: -0.0000

Data Index: 1243732 (The Pile)

Max Activating Token Index: 76

Text #13

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4016. Min Act: -0.0000

Data Index: 112405 (The Pile)

Max Activating Token Index: 428

Text #14

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4122. Min Act: -0.0000

Data Index: 1529148 (The Pile)

Max Activating Token Index: 416

Text #15

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3994. Min Act: 0.0000

Data Index: 181266 (The Pile)

Max Activating Token Index: 51

Text #16

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3992. Min Act: -0.0000

Data Index: 395627 (The Pile)

Max Activating Token Index: 24

Text #17

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4041. Min Act: -0.0000

Data Index: 695291 (The Pile)

Max Activating Token Index: 320

Text #18

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.3849. Min Act: 0.0000

Data Index: 1783189 (The Pile)

Max Activating Token Index: 186

Text #19

Max Range: 0.4874. Min Range: -0.4874

Max Act: 0.4112. Min Act: -0.0000

Data Index: 1799763 (The Pile)

Max Activating Token Index: 93