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

Dataset: The Pile

Neuron 3067 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4992. Min Act: -0.0000

Data Index: 329553 (The Pile)

Max Activating Token Index: 705

Text #1

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1064601 (The Pile)

Max Activating Token Index: 884

Text #2

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4786. Min Act: -0.0000

Data Index: 1324513 (The Pile)

Max Activating Token Index: 696

Text #3

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4840. Min Act: -0.0001

Data Index: 1249527 (The Pile)

Max Activating Token Index: 73

Text #4

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.5027. Min Act: -0.0000

Data Index: 1378006 (The Pile)

Max Activating Token Index: 775

Text #5

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4829. Min Act: -0.0000

Data Index: 1967938 (The Pile)

Max Activating Token Index: 598

Text #6

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4962. Min Act: -0.0000

Data Index: 168575 (The Pile)

Max Activating Token Index: 257

Text #7

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4767. Min Act: -0.0000

Data Index: 929536 (The Pile)

Max Activating Token Index: 991

Text #8

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4467. Min Act: -0.0000

Data Index: 1206822 (The Pile)

Max Activating Token Index: 69

Text #9

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4603. Min Act: -0.0000

Data Index: 568638 (The Pile)

Max Activating Token Index: 667

Text #10

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4479. Min Act: -0.0000

Data Index: 494679 (The Pile)

Max Activating Token Index: 402

Text #11

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4072. Min Act: -0.0000

Data Index: 789566 (The Pile)

Max Activating Token Index: 533

Text #12

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4633. Min Act: -0.0000

Data Index: 134843 (The Pile)

Max Activating Token Index: 45

Text #13

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1214917 (The Pile)

Max Activating Token Index: 367

Text #14

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1090351 (The Pile)

Max Activating Token Index: 548

Text #15

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4264. Min Act: -0.0000

Data Index: 1229436 (The Pile)

Max Activating Token Index: 269

Text #16

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.4478. Min Act: -0.0000

Data Index: 1728943 (The Pile)

Max Activating Token Index: 285

Text #17

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3646. Min Act: -0.0000

Data Index: 75491 (The Pile)

Max Activating Token Index: 807

Text #18

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3856. Min Act: -0.0000

Data Index: 1329912 (The Pile)

Max Activating Token Index: 770

Text #19

Max Range: 0.5189. Min Range: -0.5189

Max Act: 0.3995. Min Act: -0.0000

Data Index: 261661 (The Pile)

Max Activating Token Index: 292