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

Dataset: The Pile

Neuron 3352 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.6995. Min Act: -0.0000

Data Index: 33159 (The Pile)

Max Activating Token Index: 375

Text #1

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.6286. Min Act: -0.0000

Data Index: 1605484 (The Pile)

Max Activating Token Index: 399

Text #2

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.5684. Min Act: -0.0000

Data Index: 343798 (The Pile)

Max Activating Token Index: 951

Text #3

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4998. Min Act: -0.0000

Data Index: 299301 (The Pile)

Max Activating Token Index: 894

Text #4

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1174775 (The Pile)

Max Activating Token Index: 820

Text #5

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4365. Min Act: -0.0000

Data Index: 509130 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4765. Min Act: -0.0000

Data Index: 1753484 (The Pile)

Max Activating Token Index: 313

Text #7

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4695. Min Act: 0.0000

Data Index: 1806348 (The Pile)

Max Activating Token Index: 986

Text #8

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4716. Min Act: -0.0000

Data Index: 1127740 (The Pile)

Max Activating Token Index: 923

Text #9

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4559. Min Act: -0.0000

Data Index: 972657 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4958. Min Act: -0.0000

Data Index: 1585977 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4871. Min Act: -0.0000

Data Index: 439842 (The Pile)

Max Activating Token Index: 465

Text #12

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4756. Min Act: -0.0000

Data Index: 1502427 (The Pile)

Max Activating Token Index: 33

Text #13

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4527. Min Act: -0.0000

Data Index: 1202450 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4124. Min Act: -0.0000

Data Index: 241922 (The Pile)

Max Activating Token Index: 571

Text #15

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4367. Min Act: -0.0000

Data Index: 728419 (The Pile)

Max Activating Token Index: 599

Text #16

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4216. Min Act: -0.0000

Data Index: 1257143 (The Pile)

Max Activating Token Index: 1017

Text #17

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4522. Min Act: -0.0000

Data Index: 35115 (The Pile)

Max Activating Token Index: 364

Text #18

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4195. Min Act: -0.0000

Data Index: 1177365 (The Pile)

Max Activating Token Index: 286

Text #19

Max Range: 0.6995. Min Range: -0.6995

Max Act: 0.4185. Min Act: -0.0000

Data Index: 1034536 (The Pile)

Max Activating Token Index: 55