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

Dataset: The Pile

Neuron 1371 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: 0.5930. Min Range: -0.5930

Max Act: 0.5930. Min Act: -0.0000

Data Index: 508950 (The Pile)

Max Activating Token Index: 386

Text #1

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.5174. Min Act: -0.0000

Data Index: 1397557 (The Pile)

Max Activating Token Index: 44

Text #2

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4687. Min Act: -0.0000

Data Index: 1651401 (The Pile)

Max Activating Token Index: 264

Text #3

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4426. Min Act: -0.0000

Data Index: 1140621 (The Pile)

Max Activating Token Index: 973

Text #4

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4201. Min Act: -0.0000

Data Index: 1526532 (The Pile)

Max Activating Token Index: 497

Text #5

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4173. Min Act: -0.0000

Data Index: 1416025 (The Pile)

Max Activating Token Index: 803

Text #6

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4354. Min Act: -0.0000

Data Index: 1600807 (The Pile)

Max Activating Token Index: 416

Text #7

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4158. Min Act: -0.0000

Data Index: 510217 (The Pile)

Max Activating Token Index: 627

Text #8

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3659. Min Act: -0.0000

Data Index: 1889844 (The Pile)

Max Activating Token Index: 914

Text #9

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4111. Min Act: -0.0000

Data Index: 814678 (The Pile)

Max Activating Token Index: 663

Text #10

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4189. Min Act: -0.0000

Data Index: 992892 (The Pile)

Max Activating Token Index: 192

Text #11

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4350. Min Act: -0.0000

Data Index: 1698219 (The Pile)

Max Activating Token Index: 384

Text #12

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4295. Min Act: -0.0000

Data Index: 661853 (The Pile)

Max Activating Token Index: 752

Text #13

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4252. Min Act: -0.0000

Data Index: 1780380 (The Pile)

Max Activating Token Index: 397

Text #14

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4044. Min Act: -0.0000

Data Index: 1248574 (The Pile)

Max Activating Token Index: 827

Text #15

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.4143. Min Act: -0.0000

Data Index: 1631705 (The Pile)

Max Activating Token Index: 121

Text #16

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3759. Min Act: -0.0000

Data Index: 286510 (The Pile)

Max Activating Token Index: 428

Text #17

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3638. Min Act: -0.0000

Data Index: 1764168 (The Pile)

Max Activating Token Index: 819

Text #18

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3480. Min Act: -0.0000

Data Index: 566708 (The Pile)

Max Activating Token Index: 458

Text #19

Max Range: 0.5930. Min Range: -0.5930

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1088617 (The Pile)

Max Activating Token Index: 250