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

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

Neuron 2705 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1457. Min Act: -0.0000

Data Index: 26286 (C4 (Web Text))

Max Activating Token Index: 108

Text #1

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1275. Min Act: -0.0000

Data Index: 1283808 (C4 (Web Text))

Max Activating Token Index: 852

Text #2

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1270. Min Act: -0.0000

Data Index: 830170 (C4 (Web Text))

Max Activating Token Index: 662

Text #3

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1238. Min Act: -0.0000

Data Index: 397048 (C4 (Web Text))

Max Activating Token Index: 455

Text #4

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1192. Min Act: -0.0000

Data Index: 841300 (C4 (Web Text))

Max Activating Token Index: 229

Text #5

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1176. Min Act: -0.0000

Data Index: 625901 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1152132 (C4 (Web Text))

Max Activating Token Index: 342

Text #7

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1104. Min Act: -0.0000

Data Index: 476270 (C4 (Web Text))

Max Activating Token Index: 722

Text #8

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1056. Min Act: -0.0000

Data Index: 561055 (C4 (Web Text))

Max Activating Token Index: 1002

Text #9

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1043. Min Act: -0.0000

Data Index: 169884 (C4 (Web Text))

Max Activating Token Index: 95

Text #10

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1074. Min Act: -0.0000

Data Index: 778092 (C4 (Web Text))

Max Activating Token Index: 876

Text #11

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1032. Min Act: -0.0000

Data Index: 287685 (C4 (Web Text))

Max Activating Token Index: 466

Text #12

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1020. Min Act: -0.0000

Data Index: 622162 (C4 (Web Text))

Max Activating Token Index: 932

Text #13

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1085. Min Act: -0.0000

Data Index: 198034 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1047. Min Act: -0.0000

Data Index: 517990 (C4 (Web Text))

Max Activating Token Index: 664

Text #15

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.1007. Min Act: -0.0000

Data Index: 252108 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0985. Min Act: -0.0000

Data Index: 84137 (C4 (Web Text))

Max Activating Token Index: 100

Text #17

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0983. Min Act: -0.0000

Data Index: 617359 (C4 (Web Text))

Max Activating Token Index: 31

Text #18

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0984. Min Act: -0.0000

Data Index: 81656 (C4 (Web Text))

Max Activating Token Index: 637

Text #19

Max Range: 0.1457. Min Range: -0.1457

Max Act: 0.0961. Min Act: -0.0000

Data Index: 961618 (C4 (Web Text))

Max Activating Token Index: 78