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

Dataset: The Pile

Neuron 758 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: 0.2988. Min Range: -0.2988

Max Act: 0.2988. Min Act: -0.0000

Data Index: 1641150 (The Pile)

Max Activating Token Index: 546

Text #1

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1803627 (The Pile)

Max Activating Token Index: 478

Text #2

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2273. Min Act: -0.0000

Data Index: 471168 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2160. Min Act: -0.0000

Data Index: 648212 (The Pile)

Max Activating Token Index: 846

Text #4

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2132. Min Act: -0.0000

Data Index: 1427254 (The Pile)

Max Activating Token Index: 385

Text #5

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2327. Min Act: -0.0000

Data Index: 1069478 (The Pile)

Max Activating Token Index: 108

Text #6

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2117. Min Act: -0.0000

Data Index: 71876 (The Pile)

Max Activating Token Index: 990

Text #7

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2294. Min Act: -0.0000

Data Index: 1091292 (The Pile)

Max Activating Token Index: 916

Text #8

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2112. Min Act: -0.0000

Data Index: 1799710 (The Pile)

Max Activating Token Index: 649

Text #9

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2099. Min Act: -0.0000

Data Index: 1903721 (The Pile)

Max Activating Token Index: 817

Text #10

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2234. Min Act: -0.0000

Data Index: 1453351 (The Pile)

Max Activating Token Index: 420

Text #11

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2147. Min Act: -0.0000

Data Index: 1778319 (The Pile)

Max Activating Token Index: 348

Text #12

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2202. Min Act: -0.0000

Data Index: 309032 (The Pile)

Max Activating Token Index: 567

Text #13

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1947. Min Act: 0.0000

Data Index: 60025 (The Pile)

Max Activating Token Index: 960

Text #14

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1590234 (The Pile)

Max Activating Token Index: 480

Text #15

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2095. Min Act: -0.0000

Data Index: 850603 (The Pile)

Max Activating Token Index: 964

Text #16

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2210. Min Act: -0.0000

Data Index: 358120 (The Pile)

Max Activating Token Index: 799

Text #17

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.1961. Min Act: -0.0000

Data Index: 1492894 (The Pile)

Max Activating Token Index: 129

Text #18

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2078. Min Act: -0.0000

Data Index: 631513 (The Pile)

Max Activating Token Index: 1014

Text #19

Max Range: 0.2988. Min Range: -0.2988

Max Act: 0.2020. Min Act: -0.0000

Data Index: 1067861 (The Pile)

Max Activating Token Index: 928