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

Dataset: The Pile

Neuron 2543 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.3466. Min Act: -0.0000

Data Index: 448819 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2374. Min Act: -0.0000

Data Index: 846715 (The Pile)

Max Activating Token Index: 841

Text #2

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2580. Min Act: -0.0000

Data Index: 682383 (The Pile)

Max Activating Token Index: 957

Text #3

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2306. Min Act: -0.0000

Data Index: 829066 (The Pile)

Max Activating Token Index: 783

Text #4

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2263. Min Act: -0.0000

Data Index: 885348 (The Pile)

Max Activating Token Index: 889

Text #5

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2202. Min Act: -0.0000

Data Index: 1163020 (The Pile)

Max Activating Token Index: 243

Text #6

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2316. Min Act: -0.0000

Data Index: 25239 (The Pile)

Max Activating Token Index: 328

Text #7

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2099. Min Act: -0.0000

Data Index: 263083 (The Pile)

Max Activating Token Index: 851

Text #8

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2177. Min Act: -0.0000

Data Index: 345675 (The Pile)

Max Activating Token Index: 741

Text #9

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2067. Min Act: -0.0000

Data Index: 1847231 (The Pile)

Max Activating Token Index: 765

Text #10

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2102. Min Act: -0.0000

Data Index: 1826631 (The Pile)

Max Activating Token Index: 441

Text #11

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1345226 (The Pile)

Max Activating Token Index: 212

Text #12

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1908. Min Act: -0.0000

Data Index: 838408 (The Pile)

Max Activating Token Index: 854

Text #13

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1867. Min Act: -0.0000

Data Index: 3911 (The Pile)

Max Activating Token Index: 740

Text #14

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2062. Min Act: -0.0000

Data Index: 1800290 (The Pile)

Max Activating Token Index: 544

Text #15

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1780. Min Act: -0.0000

Data Index: 740368 (The Pile)

Max Activating Token Index: 858

Text #16

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.2051. Min Act: -0.0000

Data Index: 407344 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1980. Min Act: -0.0000

Data Index: 1161712 (The Pile)

Max Activating Token Index: 329

Text #18

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1749. Min Act: -0.0000

Data Index: 1423461 (The Pile)

Max Activating Token Index: 331

Text #19

Max Range: 0.3466. Min Range: -0.3466

Max Act: 0.1981. Min Act: -0.0000

Data Index: 1207912 (The Pile)

Max Activating Token Index: 739