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

Dataset: The Pile

Neuron 795 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.7446. Min Act: -0.0000

Data Index: 1836381 (The Pile)

Max Activating Token Index: 818

Text #1

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.8425. Min Act: -0.0000

Data Index: 1335957 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.4977. Min Act: -0.0000

Data Index: 160130 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.6188. Min Act: -0.0000

Data Index: 1423199 (The Pile)

Max Activating Token Index: 31

Text #4

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.5527. Min Act: -0.0000

Data Index: 1430356 (The Pile)

Max Activating Token Index: 729

Text #5

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.4807. Min Act: -0.0000

Data Index: 1736690 (The Pile)

Max Activating Token Index: 973

Text #6

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.3791. Min Act: -0.0000

Data Index: 734799 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.4531. Min Act: -0.0000

Data Index: 1949161 (The Pile)

Max Activating Token Index: 662

Text #8

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.3189. Min Act: -0.0000

Data Index: 513878 (The Pile)

Max Activating Token Index: 310

Text #9

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.4578. Min Act: -0.0000

Data Index: 967195 (The Pile)

Max Activating Token Index: 740

Text #10

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.3474. Min Act: 0.0000

Data Index: 643611 (The Pile)

Max Activating Token Index: 124

Text #11

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.1791. Min Act: -0.0000

Data Index: 693726 (The Pile)

Max Activating Token Index: 632

Text #12

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.3845. Min Act: -0.0000

Data Index: 1691382 (The Pile)

Max Activating Token Index: 180

Text #13

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.2813. Min Act: -0.0000

Data Index: 271675 (The Pile)

Max Activating Token Index: 682

Text #14

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.2562. Min Act: -0.0000

Data Index: 29085 (The Pile)

Max Activating Token Index: 780

Text #15

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.2197. Min Act: -0.0000

Data Index: 515932 (The Pile)

Max Activating Token Index: 943

Text #16

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.3016. Min Act: -0.0000

Data Index: 1382996 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.3233. Min Act: -0.0000

Data Index: 973932 (The Pile)

Max Activating Token Index: 104

Text #18

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.2318. Min Act: -0.0000

Data Index: 651413 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 1.8425. Min Range: -1.8425

Max Act: 1.2381. Min Act: -0.0000

Data Index: 151862 (The Pile)

Max Activating Token Index: 523