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

Dataset: The Pile

Neuron 3808 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: 0.3922. Min Range: -0.3922

Max Act: 0.3549. Min Act: -0.0000

Data Index: 1429995 (The Pile)

Max Activating Token Index: 157

Text #1

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.3922. Min Act: -0.0000

Data Index: 461582 (The Pile)

Max Activating Token Index: 787

Text #2

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2510. Min Act: -0.0000

Data Index: 1593965 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2991. Min Act: -0.0000

Data Index: 1295821 (The Pile)

Max Activating Token Index: 668

Text #4

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2665. Min Act: -0.0000

Data Index: 1983551 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2336. Min Act: -0.0000

Data Index: 871173 (The Pile)

Max Activating Token Index: 737

Text #6

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2703. Min Act: -0.0000

Data Index: 1381357 (The Pile)

Max Activating Token Index: 879

Text #7

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2340. Min Act: -0.0000

Data Index: 291910 (The Pile)

Max Activating Token Index: 888

Text #8

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1910300 (The Pile)

Max Activating Token Index: 586

Text #9

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2278. Min Act: -0.0000

Data Index: 1156977 (The Pile)

Max Activating Token Index: 70

Text #10

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2252. Min Act: -0.0000

Data Index: 1267442 (The Pile)

Max Activating Token Index: 988

Text #11

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2253. Min Act: -0.0000

Data Index: 1220528 (The Pile)

Max Activating Token Index: 399

Text #12

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2564. Min Act: -0.0000

Data Index: 1527064 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2441. Min Act: -0.0000

Data Index: 571965 (The Pile)

Max Activating Token Index: 445

Text #14

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.1830. Min Act: -0.0000

Data Index: 1161403 (The Pile)

Max Activating Token Index: 602

Text #15

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2115. Min Act: -0.0000

Data Index: 318089 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2423. Min Act: -0.0000

Data Index: 1815511 (The Pile)

Max Activating Token Index: 781

Text #17

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2086. Min Act: -0.0000

Data Index: 1347241 (The Pile)

Max Activating Token Index: 398

Text #18

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.2370. Min Act: -0.0000

Data Index: 1984906 (The Pile)

Max Activating Token Index: 792

Text #19

Max Range: 0.3922. Min Range: -0.3922

Max Act: 0.1970. Min Act: -0.0000

Data Index: 386713 (The Pile)

Max Activating Token Index: 626