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

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

Neuron 3401 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1665. Min Act: -0.0001

Data Index: 282180 (C4 (Web Text))

Max Activating Token Index: 179

Text #1

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1656. Min Act: -0.0002

Data Index: 516491 (C4 (Web Text))

Max Activating Token Index: 208

Text #2

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1647. Min Act: -0.0001

Data Index: 955569 (C4 (Web Text))

Max Activating Token Index: 600

Text #3

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1534. Min Act: -0.0002

Data Index: 1069068 (C4 (Web Text))

Max Activating Token Index: 928

Text #4

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1481. Min Act: -0.0002

Data Index: 746065 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1457. Min Act: -0.0002

Data Index: 458213 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1399. Min Act: -0.0002

Data Index: 601301 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1335. Min Act: -0.0002

Data Index: 958945 (C4 (Web Text))

Max Activating Token Index: 116

Text #8

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1322. Min Act: -0.0001

Data Index: 1154054 (C4 (Web Text))

Max Activating Token Index: 798

Text #9

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1305. Min Act: -0.0001

Data Index: 173755 (C4 (Web Text))

Max Activating Token Index: 113

Text #10

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1230. Min Act: -0.0001

Data Index: 1093611 (C4 (Web Text))

Max Activating Token Index: 60

Text #11

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1233. Min Act: -0.0001

Data Index: 326603 (C4 (Web Text))

Max Activating Token Index: 898

Text #12

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1160. Min Act: -0.0001

Data Index: 1184179 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1155. Min Act: -0.0002

Data Index: 376064 (C4 (Web Text))

Max Activating Token Index: 11

Text #14

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1102. Min Act: -0.0002

Data Index: 227603 (C4 (Web Text))

Max Activating Token Index: 883

Text #15

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1129. Min Act: -0.0002

Data Index: 1156960 (C4 (Web Text))

Max Activating Token Index: 375

Text #16

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1083. Min Act: -0.0001

Data Index: 382046 (C4 (Web Text))

Max Activating Token Index: 656

Text #17

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1182583 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1044. Min Act: -0.0001

Data Index: 375452 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.1665. Min Range: -0.1665

Max Act: 0.1088. Min Act: -0.0002

Data Index: 798877 (C4 (Web Text))

Max Activating Token Index: 812