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

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

Neuron 1398 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.3430. Min Act: -0.0001

Data Index: 1218441 (C4 (Web Text))

Max Activating Token Index: 41

Text #1

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.2594. Min Act: -0.0001

Data Index: 991736 (C4 (Web Text))

Max Activating Token Index: 235

Text #2

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.1211. Min Act: -0.0001

Data Index: 356105 (C4 (Web Text))

Max Activating Token Index: 788

Text #3

Max Range: 1.3430. Min Range: -1.3430

Max Act: 1.0380. Min Act: -0.0001

Data Index: 1227964 (C4 (Web Text))

Max Activating Token Index: 5

Text #4

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9418. Min Act: -0.0001

Data Index: 57898 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9626. Min Act: -0.0000

Data Index: 942490 (C4 (Web Text))

Max Activating Token Index: 878

Text #6

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.8677. Min Act: -0.0000

Data Index: 971593 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9084. Min Act: -0.0001

Data Index: 661743 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.8684. Min Act: -0.0001

Data Index: 23608 (C4 (Web Text))

Max Activating Token Index: 588

Text #9

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.8922. Min Act: -0.0001

Data Index: 388133 (C4 (Web Text))

Max Activating Token Index: 417

Text #10

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.7948. Min Act: -0.0000

Data Index: 1217278 (C4 (Web Text))

Max Activating Token Index: 985

Text #11

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.9570. Min Act: -0.0001

Data Index: 125062 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.8644. Min Act: -0.0001

Data Index: 532703 (C4 (Web Text))

Max Activating Token Index: 17

Text #13

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.7278. Min Act: -0.0000

Data Index: 430890 (C4 (Web Text))

Max Activating Token Index: 241

Text #14

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.8701. Min Act: -0.0001

Data Index: 972507 (C4 (Web Text))

Max Activating Token Index: 814

Text #15

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.7898. Min Act: -0.0001

Data Index: 1261566 (C4 (Web Text))

Max Activating Token Index: 401

Text #16

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.8375. Min Act: -0.0000

Data Index: 1147444 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.7596. Min Act: -0.0001

Data Index: 1196876 (C4 (Web Text))

Max Activating Token Index: 357

Text #18

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.7672. Min Act: -0.0001

Data Index: 1185595 (C4 (Web Text))

Max Activating Token Index: 250

Text #19

Max Range: 1.3430. Min Range: -1.3430

Max Act: 0.6821. Min Act: -0.0001

Data Index: 779818 (C4 (Web Text))

Max Activating Token Index: 12