Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4235 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0439. Min Act: -0.0002

Data Index: 410321 (C4 (Web Text))

Max Activating Token Index: 69

Text #1

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0511. Min Act: -0.0002

Data Index: 1063702 (C4 (Web Text))

Max Activating Token Index: 394

Text #2

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0442. Min Act: -0.0002

Data Index: 146508 (C4 (Web Text))

Max Activating Token Index: 824

Text #3

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0476. Min Act: -0.0002

Data Index: 111790 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0457. Min Act: -0.0002

Data Index: 1039979 (C4 (Web Text))

Max Activating Token Index: 95

Text #5

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0446. Min Act: -0.0002

Data Index: 139116 (C4 (Web Text))

Max Activating Token Index: 405

Text #6

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0390. Min Act: -0.0002

Data Index: 189185 (C4 (Web Text))

Max Activating Token Index: 89

Text #7

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0412. Min Act: -0.0002

Data Index: 79067 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0414. Min Act: -0.0002

Data Index: 1334454 (C4 (Web Text))

Max Activating Token Index: 821

Text #9

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0385. Min Act: -0.0002

Data Index: 686339 (C4 (Web Text))

Max Activating Token Index: 722

Text #10

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0390. Min Act: -0.0002

Data Index: 1047429 (C4 (Web Text))

Max Activating Token Index: 631

Text #11

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0435. Min Act: -0.0002

Data Index: 1119467 (C4 (Web Text))

Max Activating Token Index: 599

Text #12

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0410. Min Act: -0.0002

Data Index: 835948 (C4 (Web Text))

Max Activating Token Index: 853

Text #13

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0388. Min Act: -0.0002

Data Index: 1067477 (C4 (Web Text))

Max Activating Token Index: 607

Text #14

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0397. Min Act: -0.0002

Data Index: 766111 (C4 (Web Text))

Max Activating Token Index: 844

Text #15

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0368. Min Act: -0.0002

Data Index: 938888 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0432. Min Act: -0.0002

Data Index: 980362 (C4 (Web Text))

Max Activating Token Index: 152

Text #17

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0426. Min Act: -0.0002

Data Index: 1208700 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0406. Min Act: -0.0002

Data Index: 952438 (C4 (Web Text))

Max Activating Token Index: 318

Text #19

Max Range: 0.0511. Min Range: -0.0511

Max Act: 0.0341. Min Act: -0.0002

Data Index: 917572 (C4 (Web Text))

Max Activating Token Index: 726