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

Dataset: The Pile

Neuron 1270 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.2357. Min Act: -0.0000

Data Index: 648387 (The Pile)

Max Activating Token Index: 296

Text #1

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.2674. Min Act: -0.0000

Data Index: 3906 (The Pile)

Max Activating Token Index: 730

Text #2

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.1764. Min Act: -0.0000

Data Index: 853816 (The Pile)

Max Activating Token Index: 952

Text #3

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.0667. Min Act: -0.0000

Data Index: 355731 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.0630. Min Act: -0.0000

Data Index: 1191795 (The Pile)

Max Activating Token Index: 562

Text #5

Max Range: 1.2674. Min Range: -1.2674

Max Act: 1.0783. Min Act: -0.0000

Data Index: 1967109 (The Pile)

Max Activating Token Index: 158

Text #6

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9664. Min Act: -0.0000

Data Index: 869318 (The Pile)

Max Activating Token Index: 714

Text #7

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9931. Min Act: -0.0000

Data Index: 1655977 (The Pile)

Max Activating Token Index: 491

Text #8

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9705. Min Act: -0.0000

Data Index: 1863456 (The Pile)

Max Activating Token Index: 329

Text #9

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1580524 (The Pile)

Max Activating Token Index: 639

Text #10

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8851. Min Act: -0.0000

Data Index: 1374768 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9051. Min Act: -0.0000

Data Index: 993423 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9242. Min Act: -0.0000

Data Index: 322298 (The Pile)

Max Activating Token Index: 782

Text #13

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9154. Min Act: -0.0000

Data Index: 14059 (The Pile)

Max Activating Token Index: 325

Text #14

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8850. Min Act: -0.0000

Data Index: 1799775 (The Pile)

Max Activating Token Index: 741

Text #15

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.9057. Min Act: -0.0000

Data Index: 1544471 (The Pile)

Max Activating Token Index: 887

Text #16

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8769. Min Act: 0.0001

Data Index: 1090274 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8983. Min Act: -0.0000

Data Index: 1601556 (The Pile)

Max Activating Token Index: 1010

Text #18

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8779. Min Act: -0.0000

Data Index: 117764 (The Pile)

Max Activating Token Index: 651

Text #19

Max Range: 1.2674. Min Range: -1.2674

Max Act: 0.8883. Min Act: -0.0000

Data Index: 204296 (The Pile)

Max Activating Token Index: 236