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

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

Neuron 21 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1312. Min Act: -0.0002

Data Index: 801990 (C4 (Web Text))

Max Activating Token Index: 479

Text #1

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1285. Min Act: -0.0002

Data Index: 901698 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1362. Min Act: -0.0002

Data Index: 798665 (C4 (Web Text))

Max Activating Token Index: 47

Text #3

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1208. Min Act: -0.0002

Data Index: 297534 (C4 (Web Text))

Max Activating Token Index: 760

Text #4

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1238. Min Act: -0.0002

Data Index: 491106 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1220. Min Act: -0.0002

Data Index: 1124182 (C4 (Web Text))

Max Activating Token Index: 796

Text #6

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1256. Min Act: -0.0002

Data Index: 1109661 (C4 (Web Text))

Max Activating Token Index: 679

Text #7

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1176. Min Act: -0.0002

Data Index: 689458 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1199. Min Act: -0.0002

Data Index: 693094 (C4 (Web Text))

Max Activating Token Index: 255

Text #9

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1169. Min Act: -0.0002

Data Index: 53089 (C4 (Web Text))

Max Activating Token Index: 907

Text #10

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1167. Min Act: -0.0002

Data Index: 167238 (C4 (Web Text))

Max Activating Token Index: 458

Text #11

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1267. Min Act: -0.0002

Data Index: 488923 (C4 (Web Text))

Max Activating Token Index: 73

Text #12

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1125. Min Act: -0.0002

Data Index: 687186 (C4 (Web Text))

Max Activating Token Index: 11

Text #13

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1169. Min Act: -0.0002

Data Index: 110672 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1074. Min Act: -0.0002

Data Index: 1250528 (C4 (Web Text))

Max Activating Token Index: 129

Text #15

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1069. Min Act: -0.0002

Data Index: 19779 (C4 (Web Text))

Max Activating Token Index: 132

Text #16

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1032. Min Act: -0.0002

Data Index: 935208 (C4 (Web Text))

Max Activating Token Index: 350

Text #17

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1104. Min Act: -0.0002

Data Index: 774408 (C4 (Web Text))

Max Activating Token Index: 154

Text #18

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1121. Min Act: -0.0002

Data Index: 416941 (C4 (Web Text))

Max Activating Token Index: 602

Text #19

Max Range: 0.1362. Min Range: -0.1362

Max Act: 0.1131. Min Act: -0.0002

Data Index: 622753 (C4 (Web Text))

Max Activating Token Index: 233