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

Dataset: The Pile

Neuron 90 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: 1.2885. Min Range: -1.2885

Max Act: 1.2885. Min Act: -0.0000

Data Index: 649087 (The Pile)

Max Activating Token Index: 829

Text #1

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2197. Min Act: -0.0000

Data Index: 997854 (The Pile)

Max Activating Token Index: 540

Text #2

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2000. Min Act: -0.0000

Data Index: 651615 (The Pile)

Max Activating Token Index: 662

Text #3

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.1697. Min Act: -0.0000

Data Index: 1628351 (The Pile)

Max Activating Token Index: 843

Text #4

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.2080. Min Act: -0.0000

Data Index: 328356 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9654. Min Act: -0.0000

Data Index: 1517334 (The Pile)

Max Activating Token Index: 824

Text #6

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.0107. Min Act: -0.0000

Data Index: 1059935 (The Pile)

Max Activating Token Index: 97

Text #7

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.0415. Min Act: -0.0000

Data Index: 874218 (The Pile)

Max Activating Token Index: 452

Text #8

Max Range: 1.2885. Min Range: -1.2885

Max Act: 1.0266. Min Act: -0.0000

Data Index: 1693951 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9649. Min Act: -0.0000

Data Index: 627823 (The Pile)

Max Activating Token Index: 914

Text #10

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9397. Min Act: -0.0000

Data Index: 1609994 (The Pile)

Max Activating Token Index: 238

Text #11

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1495563 (The Pile)

Max Activating Token Index: 858

Text #12

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9421. Min Act: -0.0000

Data Index: 1452961 (The Pile)

Max Activating Token Index: 262

Text #13

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9393. Min Act: -0.0000

Data Index: 1522619 (The Pile)

Max Activating Token Index: 575

Text #14

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1084325 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.9050. Min Act: -0.0000

Data Index: 900332 (The Pile)

Max Activating Token Index: 633

Text #16

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8791. Min Act: -0.0000

Data Index: 999806 (The Pile)

Max Activating Token Index: 442

Text #17

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8942. Min Act: -0.0000

Data Index: 947365 (The Pile)

Max Activating Token Index: 426

Text #18

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8933. Min Act: -0.0000

Data Index: 1955267 (The Pile)

Max Activating Token Index: 969

Text #19

Max Range: 1.2885. Min Range: -1.2885

Max Act: 0.8924. Min Act: -0.0000

Data Index: 657965 (The Pile)

Max Activating Token Index: 878