Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 3491 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 5.1441. Min Range: -5.1441

Max Act: 5.1441. Min Act: -0.0000

Data Index: 1835821 (The Pile)

Max Activating Token Index: 70

Text #1

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.3938. Min Act: -0.0000

Data Index: 1586299 (The Pile)

Max Activating Token Index: 113

Text #2

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.3493. Min Act: -0.0000

Data Index: 430726 (The Pile)

Max Activating Token Index: 422

Text #3

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.5353. Min Act: -0.0000

Data Index: 307255 (The Pile)

Max Activating Token Index: 237

Text #4

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.5066. Min Act: -0.0000

Data Index: 1164761 (The Pile)

Max Activating Token Index: 421

Text #5

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.6276. Min Act: -0.0000

Data Index: 984861 (The Pile)

Max Activating Token Index: 817

Text #6

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.6074. Min Act: -0.0000

Data Index: 853722 (The Pile)

Max Activating Token Index: 198

Text #7

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.3953. Min Act: -0.0000

Data Index: 1092556 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.0230. Min Act: -0.0000

Data Index: 1133410 (The Pile)

Max Activating Token Index: 73

Text #9

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.1421. Min Act: -0.0000

Data Index: 1033558 (The Pile)

Max Activating Token Index: 828

Text #10

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.5977. Min Act: -0.0000

Data Index: 1494740 (The Pile)

Max Activating Token Index: 636

Text #11

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.5051. Min Act: -0.0000

Data Index: 875242 (The Pile)

Max Activating Token Index: 611

Text #12

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.0305. Min Act: -0.0000

Data Index: 577427 (The Pile)

Max Activating Token Index: 498

Text #13

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.1746. Min Act: -0.0000

Data Index: 440162 (The Pile)

Max Activating Token Index: 218

Text #14

Max Range: 5.1441. Min Range: -5.1441

Max Act: 4.0200. Min Act: -0.0000

Data Index: 1501703 (The Pile)

Max Activating Token Index: 289

Text #15

Max Range: 5.1441. Min Range: -5.1441

Max Act: 3.9930. Min Act: -0.0000

Data Index: 279965 (The Pile)

Max Activating Token Index: 481

Text #16

Max Range: 5.1441. Min Range: -5.1441

Max Act: 3.9748. Min Act: -0.0000

Data Index: 1568591 (The Pile)

Max Activating Token Index: 29

Text #17

Max Range: 5.1441. Min Range: -5.1441

Max Act: 3.9814. Min Act: -0.0000

Data Index: 995106 (The Pile)

Max Activating Token Index: 314

Text #18

Max Range: 5.1441. Min Range: -5.1441

Max Act: 3.8084. Min Act: -0.0000

Data Index: 670814 (The Pile)

Max Activating Token Index: 98

Text #19

Max Range: 5.1441. Min Range: -5.1441

Max Act: 3.9666. Min Act: -0.0000

Data Index: 1562434 (The Pile)

Max Activating Token Index: 477