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

Dataset: The Pile

Neuron 1413 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: 0.3490. Min Range: -0.3490

Max Act: 0.3448. Min Act: -0.0000

Data Index: 1713731 (The Pile)

Max Activating Token Index: 793

Text #1

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3490. Min Act: -0.0000

Data Index: 788756 (The Pile)

Max Activating Token Index: 569

Text #2

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3271. Min Act: -0.0000

Data Index: 356430 (The Pile)

Max Activating Token Index: 545

Text #3

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1551796 (The Pile)

Max Activating Token Index: 416

Text #4

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2874. Min Act: -0.0000

Data Index: 1219051 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2901. Min Act: -0.0000

Data Index: 1317941 (The Pile)

Max Activating Token Index: 486

Text #6

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1371302 (The Pile)

Max Activating Token Index: 850

Text #7

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2712. Min Act: -0.0000

Data Index: 973259 (The Pile)

Max Activating Token Index: 833

Text #8

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2444. Min Act: -0.0000

Data Index: 1072920 (The Pile)

Max Activating Token Index: 210

Text #9

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2412. Min Act: -0.0000

Data Index: 378439 (The Pile)

Max Activating Token Index: 242

Text #10

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2451. Min Act: -0.0000

Data Index: 749926 (The Pile)

Max Activating Token Index: 574

Text #11

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2230. Min Act: -0.0000

Data Index: 203536 (The Pile)

Max Activating Token Index: 121

Text #12

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2066. Min Act: -0.0000

Data Index: 822414 (The Pile)

Max Activating Token Index: 882

Text #13

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2221. Min Act: -0.0000

Data Index: 574160 (The Pile)

Max Activating Token Index: 854

Text #14

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2163. Min Act: 0.0000

Data Index: 1829868 (The Pile)

Max Activating Token Index: 839

Text #15

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2110. Min Act: -0.0000

Data Index: 528669 (The Pile)

Max Activating Token Index: 498

Text #16

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2019. Min Act: -0.0000

Data Index: 1947468 (The Pile)

Max Activating Token Index: 944

Text #17

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2034. Min Act: -0.0000

Data Index: 1085601 (The Pile)

Max Activating Token Index: 208

Text #18

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.2029. Min Act: -0.0000

Data Index: 502280 (The Pile)

Max Activating Token Index: 138

Text #19

Max Range: 0.3490. Min Range: -0.3490

Max Act: 0.1942. Min Act: -0.0000

Data Index: 1954100 (The Pile)

Max Activating Token Index: 896