Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1120 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1692. Min Act: -0.0001

Data Index: 1171325 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1678. Min Act: -0.0000

Data Index: 451212 (C4 (Web Text))

Max Activating Token Index: 108

Text #2

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1475. Min Act: -0.0000

Data Index: 168785 (C4 (Web Text))

Max Activating Token Index: 252

Text #3

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1443. Min Act: -0.0001

Data Index: 167503 (C4 (Web Text))

Max Activating Token Index: 73

Text #4

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1420. Min Act: -0.0000

Data Index: 693173 (C4 (Web Text))

Max Activating Token Index: 912

Text #5

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1440. Min Act: -0.0000

Data Index: 1148314 (C4 (Web Text))

Max Activating Token Index: 377

Text #6

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1348. Min Act: -0.0001

Data Index: 795870 (C4 (Web Text))

Max Activating Token Index: 725

Text #7

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1280. Min Act: -0.0000

Data Index: 192573 (C4 (Web Text))

Max Activating Token Index: 439

Text #8

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1322. Min Act: -0.0000

Data Index: 816902 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1154. Min Act: -0.0001

Data Index: 523503 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1214. Min Act: -0.0000

Data Index: 1192004 (C4 (Web Text))

Max Activating Token Index: 379

Text #11

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1091. Min Act: -0.0001

Data Index: 640584 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1086. Min Act: -0.0000

Data Index: 111648 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1126. Min Act: -0.0001

Data Index: 690728 (C4 (Web Text))

Max Activating Token Index: 870

Text #14

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1240. Min Act: -0.0001

Data Index: 8404 (C4 (Web Text))

Max Activating Token Index: 970

Text #15

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1101. Min Act: -0.0000

Data Index: 675436 (C4 (Web Text))

Max Activating Token Index: 881

Text #16

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1053. Min Act: -0.0000

Data Index: 201975 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1042. Min Act: -0.0000

Data Index: 796511 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1083. Min Act: -0.0001

Data Index: 780375 (C4 (Web Text))

Max Activating Token Index: 621

Text #19

Max Range: 0.1692. Min Range: -0.1692

Max Act: 0.1078. Min Act: -0.0000

Data Index: 1004641 (C4 (Web Text))

Max Activating Token Index: 16