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

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

Neuron 4333 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: 0.1677. Min Range: -0.1677

Max Act: 0.1677. Min Act: -0.0002

Data Index: 1286380 (C4 (Web Text))

Max Activating Token Index: 828

Text #1

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1292. Min Act: -0.0002

Data Index: 218549 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1304. Min Act: -0.0002

Data Index: 1071449 (C4 (Web Text))

Max Activating Token Index: 761

Text #3

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1362. Min Act: -0.0002

Data Index: 368847 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1211. Min Act: -0.0002

Data Index: 689346 (C4 (Web Text))

Max Activating Token Index: 572

Text #5

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1135. Min Act: -0.0002

Data Index: 1245379 (C4 (Web Text))

Max Activating Token Index: 265

Text #6

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1160. Min Act: -0.0002

Data Index: 594407 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1181. Min Act: -0.0002

Data Index: 1209071 (C4 (Web Text))

Max Activating Token Index: 958

Text #8

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1035. Min Act: -0.0002

Data Index: 510274 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1245. Min Act: -0.0002

Data Index: 863672 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1204. Min Act: -0.0002

Data Index: 809515 (C4 (Web Text))

Max Activating Token Index: 150

Text #11

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1085. Min Act: -0.0002

Data Index: 457574 (C4 (Web Text))

Max Activating Token Index: 443

Text #12

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1103. Min Act: -0.0002

Data Index: 394939 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1102. Min Act: -0.0002

Data Index: 200496 (C4 (Web Text))

Max Activating Token Index: 445

Text #14

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1114. Min Act: -0.0002

Data Index: 997229 (C4 (Web Text))

Max Activating Token Index: 396

Text #15

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1125. Min Act: -0.0002

Data Index: 362029 (C4 (Web Text))

Max Activating Token Index: 468

Text #16

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.0964. Min Act: -0.0002

Data Index: 756446 (C4 (Web Text))

Max Activating Token Index: 752

Text #17

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1066. Min Act: -0.0002

Data Index: 162019 (C4 (Web Text))

Max Activating Token Index: 157

Text #18

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1106. Min Act: -0.0002

Data Index: 607328 (C4 (Web Text))

Max Activating Token Index: 135

Text #19

Max Range: 0.1677. Min Range: -0.1677

Max Act: 0.1107. Min Act: -0.0002

Data Index: 360544 (C4 (Web Text))

Max Activating Token Index: 319