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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 3156 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1215. Min Act: -0.0000

Data Index: 998848 (C4 (Web Text))

Max Activating Token Index: 953

Text #1

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1149. Min Act: -0.0000

Data Index: 869126 (C4 (Web Text))

Max Activating Token Index: 959

Text #2

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1180. Min Act: -0.0000

Data Index: 717903 (C4 (Web Text))

Max Activating Token Index: 766

Text #3

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1216. Min Act: -0.0000

Data Index: 471456 (C4 (Web Text))

Max Activating Token Index: 450

Text #4

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1195. Min Act: -0.0000

Data Index: 511828 (C4 (Web Text))

Max Activating Token Index: 364

Text #5

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1127. Min Act: -0.0000

Data Index: 1148191 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1107492 (C4 (Web Text))

Max Activating Token Index: 24

Text #7

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1119. Min Act: -0.0000

Data Index: 1224331 (C4 (Web Text))

Max Activating Token Index: 840

Text #8

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1042. Min Act: -0.0000

Data Index: 354827 (C4 (Web Text))

Max Activating Token Index: 585

Text #9

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1063. Min Act: -0.0000

Data Index: 689525 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1116. Min Act: -0.0000

Data Index: 1178498 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1023. Min Act: -0.0001

Data Index: 852381 (C4 (Web Text))

Max Activating Token Index: 84

Text #12

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0968. Min Act: -0.0001

Data Index: 820787 (C4 (Web Text))

Max Activating Token Index: 913

Text #13

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0954. Min Act: -0.0000

Data Index: 389241 (C4 (Web Text))

Max Activating Token Index: 24

Text #14

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1013. Min Act: -0.0000

Data Index: 1056552 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1005. Min Act: -0.0000

Data Index: 490056 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0947. Min Act: -0.0000

Data Index: 1258799 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0976. Min Act: -0.0000

Data Index: 719378 (C4 (Web Text))

Max Activating Token Index: 707

Text #18

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.0966. Min Act: -0.0000

Data Index: 48920 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.1216. Min Range: -0.1216

Max Act: 0.1032. Min Act: -0.0000

Data Index: 941629 (C4 (Web Text))

Max Activating Token Index: 692