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

Dataset: The Pile

Neuron 4024 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0280. Min Act: -0.0000

Data Index: 1124701 (The Pile)

Max Activating Token Index: 1009

Text #1

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0252. Min Act: -0.0000

Data Index: 428277 (The Pile)

Max Activating Token Index: 1021

Text #2

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0254. Min Act: -0.0000

Data Index: 1208773 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0251. Min Act: -0.0000

Data Index: 57821 (The Pile)

Max Activating Token Index: 1018

Text #4

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0249. Min Act: 0.0000

Data Index: 1112824 (The Pile)

Max Activating Token Index: 1002

Text #5

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0248. Min Act: -0.0000

Data Index: 857927 (The Pile)

Max Activating Token Index: 910

Text #6

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0242. Min Act: -0.0000

Data Index: 1371511 (The Pile)

Max Activating Token Index: 967

Text #7

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0250. Min Act: -0.0000

Data Index: 5640 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0242. Min Act: -0.0000

Data Index: 590210 (The Pile)

Max Activating Token Index: 986

Text #9

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0000

Data Index: 689307 (The Pile)

Max Activating Token Index: 1016

Text #10

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0241. Min Act: -0.0000

Data Index: 979969 (The Pile)

Max Activating Token Index: 975

Text #11

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0240. Min Act: -0.0000

Data Index: 1448701 (The Pile)

Max Activating Token Index: 950

Text #12

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0238. Min Act: 0.0000

Data Index: 705969 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0229. Min Act: -0.0000

Data Index: 1683923 (The Pile)

Max Activating Token Index: 1018

Text #14

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0237. Min Act: -0.0000

Data Index: 235931 (The Pile)

Max Activating Token Index: 1022

Text #15

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0236. Min Act: -0.0000

Data Index: 1807403 (The Pile)

Max Activating Token Index: 952

Text #16

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0244. Min Act: -0.0000

Data Index: 417389 (The Pile)

Max Activating Token Index: 1022

Text #17

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1869727 (The Pile)

Max Activating Token Index: 961

Text #18

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1968003 (The Pile)

Max Activating Token Index: 906

Text #19

Max Range: 0.0280. Min Range: -0.0280

Max Act: 0.0235. Min Act: -0.0000

Data Index: 64221 (The Pile)

Max Activating Token Index: 1019