Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1972 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.7514. Min Act: -0.0005

Data Index: 314822 (C4 (Web Text))

Max Activating Token Index: 816

Text #1

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.6707. Min Act: -0.0005

Data Index: 1422031 (Python Code)

Max Activating Token Index: 245

Text #2

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.5983. Min Act: -0.0005

Data Index: 837331 (C4 (Web Text))

Max Activating Token Index: 811

Text #3

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.4075. Min Act: -0.0005

Data Index: 1318778 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.3466. Min Act: -0.0005

Data Index: 780700 (C4 (Web Text))

Max Activating Token Index: 248

Text #5

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.3255. Min Act: -0.0005

Data Index: 422869 (C4 (Web Text))

Max Activating Token Index: 95

Text #6

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.2484. Min Act: -0.0005

Data Index: 1388406 (Python Code)

Max Activating Token Index: 857

Text #7

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.2261. Min Act: -0.0005

Data Index: 1105038 (C4 (Web Text))

Max Activating Token Index: 861

Text #8

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.1918. Min Act: -0.0005

Data Index: 1609712 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.1621. Min Act: -0.0005

Data Index: 47878 (C4 (Web Text))

Max Activating Token Index: 553

Text #10

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.1473. Min Act: -0.0005

Data Index: 1572470 (Python Code)

Max Activating Token Index: 605

Text #11

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.1068. Min Act: -0.0005

Data Index: 1281704 (C4 (Web Text))

Max Activating Token Index: 329

Text #12

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.2151. Min Act: -0.0005

Data Index: 901669 (C4 (Web Text))

Max Activating Token Index: 977

Text #13

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.1294. Min Act: -0.0005

Data Index: 493105 (C4 (Web Text))

Max Activating Token Index: 371

Text #14

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.1448. Min Act: -0.0005

Data Index: 1427905 (Python Code)

Max Activating Token Index: 185

Text #15

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.0696. Min Act: -0.0005

Data Index: 366062 (C4 (Web Text))

Max Activating Token Index: 923

Text #16

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.1244. Min Act: -0.0005

Data Index: 1487063 (Python Code)

Max Activating Token Index: 612

Text #17

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.1063. Min Act: -0.0005

Data Index: 1031532 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.0831. Min Act: -0.0005

Data Index: 1411172 (Python Code)

Max Activating Token Index: 227

Text #19

Max Range: 0.7514. Min Range: -0.7514

Max Act: 0.0297. Min Act: -0.0005

Data Index: 1114942 (C4 (Web Text))

Max Activating Token Index: 52