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

Dataset: The Pile

Neuron 3874 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: 0.5171. Min Range: -0.5171

Max Act: 0.5171. Min Act: -0.0000

Data Index: 855951 (The Pile)

Max Activating Token Index: 983

Text #1

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4244. Min Act: -0.0000

Data Index: 194767 (The Pile)

Max Activating Token Index: 843

Text #2

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4657. Min Act: -0.0000

Data Index: 161903 (The Pile)

Max Activating Token Index: 935

Text #3

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4360. Min Act: -0.0000

Data Index: 348533 (The Pile)

Max Activating Token Index: 933

Text #4

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4221. Min Act: -0.0000

Data Index: 619064 (The Pile)

Max Activating Token Index: 708

Text #5

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4028. Min Act: -0.0000

Data Index: 216718 (The Pile)

Max Activating Token Index: 972

Text #6

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4266. Min Act: -0.0000

Data Index: 196049 (The Pile)

Max Activating Token Index: 972

Text #7

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4006. Min Act: -0.0000

Data Index: 988617 (The Pile)

Max Activating Token Index: 590

Text #8

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4308. Min Act: -0.0000

Data Index: 1556179 (The Pile)

Max Activating Token Index: 922

Text #9

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4362. Min Act: -0.0000

Data Index: 1470356 (The Pile)

Max Activating Token Index: 768

Text #10

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4247. Min Act: -0.0000

Data Index: 442724 (The Pile)

Max Activating Token Index: 696

Text #11

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4125. Min Act: -0.0000

Data Index: 282030 (The Pile)

Max Activating Token Index: 373

Text #12

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4006. Min Act: -0.0000

Data Index: 254593 (The Pile)

Max Activating Token Index: 380

Text #13

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3975. Min Act: -0.0000

Data Index: 225569 (The Pile)

Max Activating Token Index: 372

Text #14

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4082. Min Act: 0.0000

Data Index: 1051075 (The Pile)

Max Activating Token Index: 187

Text #15

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3915. Min Act: -0.0000

Data Index: 94226 (The Pile)

Max Activating Token Index: 664

Text #16

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3960. Min Act: -0.0000

Data Index: 507002 (The Pile)

Max Activating Token Index: 679

Text #17

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3683. Min Act: -0.0000

Data Index: 1679146 (The Pile)

Max Activating Token Index: 662

Text #18

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.4018. Min Act: -0.0000

Data Index: 1553241 (The Pile)

Max Activating Token Index: 506

Text #19

Max Range: 0.5171. Min Range: -0.5171

Max Act: 0.3487. Min Act: -0.0000

Data Index: 1080710 (The Pile)

Max Activating Token Index: 782