Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5520 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1207. Min Act: -0.0000

Data Index: 101544 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1165. Min Act: -0.0000

Data Index: 108864 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1231. Min Act: -0.0000

Data Index: 1274673 (C4 (Web Text))

Max Activating Token Index: 330

Text #3

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1103. Min Act: -0.0000

Data Index: 678195 (C4 (Web Text))

Max Activating Token Index: 192

Text #4

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1082. Min Act: -0.0000

Data Index: 1530194 (Python Code)

Max Activating Token Index: 926

Text #5

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1110. Min Act: -0.0000

Data Index: 1000106 (C4 (Web Text))

Max Activating Token Index: 424

Text #6

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.1043. Min Act: -0.0000

Data Index: 1635688 (Python Code)

Max Activating Token Index: 76

Text #7

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0965. Min Act: -0.0000

Data Index: 1228943 (C4 (Web Text))

Max Activating Token Index: 771

Text #8

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0945. Min Act: -0.0000

Data Index: 413586 (C4 (Web Text))

Max Activating Token Index: 187

Text #9

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1317137 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0885. Min Act: -0.0000

Data Index: 1378462 (Python Code)

Max Activating Token Index: 871

Text #11

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0928. Min Act: -0.0000

Data Index: 1383845 (Python Code)

Max Activating Token Index: 133

Text #12

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0945. Min Act: -0.0000

Data Index: 1097584 (C4 (Web Text))

Max Activating Token Index: 337

Text #13

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0932. Min Act: -0.0000

Data Index: 264336 (C4 (Web Text))

Max Activating Token Index: 635

Text #14

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0924. Min Act: -0.0000

Data Index: 1291780 (C4 (Web Text))

Max Activating Token Index: 639

Text #15

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0855. Min Act: -0.0000

Data Index: 156569 (C4 (Web Text))

Max Activating Token Index: 798

Text #16

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1630724 (Python Code)

Max Activating Token Index: 789

Text #17

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0920. Min Act: -0.0000

Data Index: 1517903 (Python Code)

Max Activating Token Index: 209

Text #18

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1532774 (Python Code)

Max Activating Token Index: 606

Text #19

Max Range: 0.1231. Min Range: -0.1231

Max Act: 0.0846. Min Act: -0.0000

Data Index: 799619 (C4 (Web Text))

Max Activating Token Index: 326