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

Dataset: The Pile

Neuron 1504 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: 0.3297. Min Range: -0.3297

Max Act: 0.3215. Min Act: -0.0000

Data Index: 712499 (The Pile)

Max Activating Token Index: 243

Text #1

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.3297. Min Act: -0.0000

Data Index: 1601502 (The Pile)

Max Activating Token Index: 377

Text #2

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2940. Min Act: -0.0000

Data Index: 358676 (The Pile)

Max Activating Token Index: 311

Text #3

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2509. Min Act: -0.0000

Data Index: 436235 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2635. Min Act: -0.0000

Data Index: 795935 (The Pile)

Max Activating Token Index: 328

Text #5

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2276. Min Act: -0.0000

Data Index: 875750 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2154. Min Act: -0.0000

Data Index: 1304196 (The Pile)

Max Activating Token Index: 555

Text #7

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.1927. Min Act: -0.0000

Data Index: 757739 (The Pile)

Max Activating Token Index: 898

Text #8

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2225. Min Act: -0.0000

Data Index: 580272 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2812. Min Act: -0.0000

Data Index: 1448529 (The Pile)

Max Activating Token Index: 961

Text #10

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2417. Min Act: -0.0000

Data Index: 1502558 (The Pile)

Max Activating Token Index: 755

Text #11

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2331. Min Act: -0.0000

Data Index: 301059 (The Pile)

Max Activating Token Index: 33

Text #12

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2233. Min Act: -0.0000

Data Index: 557431 (The Pile)

Max Activating Token Index: 497

Text #13

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2629. Min Act: -0.0000

Data Index: 1991563 (The Pile)

Max Activating Token Index: 759

Text #14

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2046. Min Act: -0.0000

Data Index: 4630 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2341. Min Act: -0.0000

Data Index: 860009 (The Pile)

Max Activating Token Index: 528

Text #16

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2314. Min Act: -0.0000

Data Index: 989060 (The Pile)

Max Activating Token Index: 324

Text #17

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2654. Min Act: -0.0000

Data Index: 1480872 (The Pile)

Max Activating Token Index: 578

Text #18

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2080. Min Act: -0.0000

Data Index: 988658 (The Pile)

Max Activating Token Index: 931

Text #19

Max Range: 0.3297. Min Range: -0.3297

Max Act: 0.2263. Min Act: -0.0000

Data Index: 1160895 (The Pile)

Max Activating Token Index: 106