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

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

Neuron 1771 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: 1.4090. Min Range: -1.4090

Max Act: 1.4090. Min Act: -0.0000

Data Index: 1070110 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1346. Min Act: -0.0000

Data Index: 1167666 (C4 (Web Text))

Max Activating Token Index: 120

Text #2

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.1178. Min Act: -0.0000

Data Index: 40798 (C4 (Web Text))

Max Activating Token Index: 482

Text #3

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9159. Min Act: -0.0000

Data Index: 1210999 (C4 (Web Text))

Max Activating Token Index: 685

Text #4

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9769. Min Act: -0.0000

Data Index: 152527 (C4 (Web Text))

Max Activating Token Index: 72

Text #5

Max Range: 1.4090. Min Range: -1.4090

Max Act: 1.0042. Min Act: -0.0000

Data Index: 528505 (C4 (Web Text))

Max Activating Token Index: 618

Text #6

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8765. Min Act: -0.0000

Data Index: 1175668 (C4 (Web Text))

Max Activating Token Index: 986

Text #7

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9825. Min Act: -0.0000

Data Index: 104824 (C4 (Web Text))

Max Activating Token Index: 281

Text #8

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8630. Min Act: -0.0000

Data Index: 1083678 (C4 (Web Text))

Max Activating Token Index: 176

Text #9

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1613144 (Python Code)

Max Activating Token Index: 601

Text #10

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.9863. Min Act: -0.0000

Data Index: 707454 (C4 (Web Text))

Max Activating Token Index: 514

Text #11

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8679. Min Act: -0.0000

Data Index: 1584325 (Python Code)

Max Activating Token Index: 524

Text #12

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.7229. Min Act: -0.0000

Data Index: 338823 (C4 (Web Text))

Max Activating Token Index: 875

Text #13

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8493. Min Act: -0.0000

Data Index: 647690 (C4 (Web Text))

Max Activating Token Index: 919

Text #14

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8242. Min Act: -0.0000

Data Index: 4243 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8695. Min Act: -0.0000

Data Index: 1379704 (Python Code)

Max Activating Token Index: 418

Text #16

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8331. Min Act: -0.0000

Data Index: 988345 (C4 (Web Text))

Max Activating Token Index: 20

Text #17

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8226. Min Act: -0.0000

Data Index: 1041054 (C4 (Web Text))

Max Activating Token Index: 496

Text #18

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8482. Min Act: -0.0000

Data Index: 1465854 (Python Code)

Max Activating Token Index: 26

Text #19

Max Range: 1.4090. Min Range: -1.4090

Max Act: 0.8429. Min Act: -0.0000

Data Index: 1462862 (Python Code)

Max Activating Token Index: 419