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

Dataset: The Pile

Neuron 1076 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.2325. Min Act: -0.0000

Data Index: 785495 (The Pile)

Max Activating Token Index: 172

Text #1

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1604. Min Act: -0.0000

Data Index: 1051504 (The Pile)

Max Activating Token Index: 750

Text #2

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1544. Min Act: -0.0000

Data Index: 358770 (The Pile)

Max Activating Token Index: 345

Text #3

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1100. Min Act: -0.0000

Data Index: 1409371 (The Pile)

Max Activating Token Index: 188

Text #4

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1810. Min Act: -0.0000

Data Index: 513129 (The Pile)

Max Activating Token Index: 806

Text #5

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1312. Min Act: -0.0000

Data Index: 197376 (The Pile)

Max Activating Token Index: 91

Text #6

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1135. Min Act: -0.0000

Data Index: 1505866 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1326. Min Act: -0.0000

Data Index: 67052 (The Pile)

Max Activating Token Index: 796

Text #8

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1302. Min Act: -0.0000

Data Index: 1232917 (The Pile)

Max Activating Token Index: 1023

Text #9

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1019. Min Act: -0.0000

Data Index: 57305 (The Pile)

Max Activating Token Index: 1015

Text #10

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.0952. Min Act: -0.0000

Data Index: 189010 (The Pile)

Max Activating Token Index: 940

Text #11

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1160. Min Act: -0.0000

Data Index: 858429 (The Pile)

Max Activating Token Index: 129

Text #12

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1726456 (The Pile)

Max Activating Token Index: 17

Text #13

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1094. Min Act: -0.0000

Data Index: 1246293 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1128. Min Act: -0.0000

Data Index: 302689 (The Pile)

Max Activating Token Index: 234

Text #15

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1158. Min Act: -0.0000

Data Index: 1194967 (The Pile)

Max Activating Token Index: 44

Text #16

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1035. Min Act: -0.0000

Data Index: 480138 (The Pile)

Max Activating Token Index: 312

Text #17

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1022. Min Act: -0.0000

Data Index: 75061 (The Pile)

Max Activating Token Index: 542

Text #18

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.0954. Min Act: -0.0000

Data Index: 1018741 (The Pile)

Max Activating Token Index: 25

Text #19

Max Range: 0.2325. Min Range: -0.2325

Max Act: 0.1027. Min Act: -0.0000

Data Index: 1355363 (The Pile)

Max Activating Token Index: 482