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

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

Neuron 3638 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8945. Min Act: -0.0000

Data Index: 822016 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8489. Min Act: -0.0000

Data Index: 648781 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8909. Min Act: -0.0000

Data Index: 906593 (C4 (Web Text))

Max Activating Token Index: 336

Text #3

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8317. Min Act: -0.0000

Data Index: 938959 (C4 (Web Text))

Max Activating Token Index: 259

Text #4

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7958. Min Act: -0.0000

Data Index: 1357559 (C4 (Web Text))

Max Activating Token Index: 540

Text #5

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8086. Min Act: 0.0001

Data Index: 253626 (C4 (Web Text))

Max Activating Token Index: 705

Text #6

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8001. Min Act: -0.0000

Data Index: 1242019 (C4 (Web Text))

Max Activating Token Index: 544

Text #7

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8225. Min Act: 0.0001

Data Index: 206459 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7651. Min Act: 0.0000

Data Index: 198870 (C4 (Web Text))

Max Activating Token Index: 604

Text #9

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.8151. Min Act: -0.0000

Data Index: 818522 (C4 (Web Text))

Max Activating Token Index: 401

Text #10

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7614. Min Act: 0.0001

Data Index: 611579 (C4 (Web Text))

Max Activating Token Index: 530

Text #11

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7739. Min Act: 0.0000

Data Index: 1330067 (C4 (Web Text))

Max Activating Token Index: 564

Text #12

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7452. Min Act: -0.0000

Data Index: 771160 (C4 (Web Text))

Max Activating Token Index: 711

Text #13

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7676. Min Act: -0.0000

Data Index: 22855 (C4 (Web Text))

Max Activating Token Index: 355

Text #14

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7127. Min Act: -0.0000

Data Index: 573983 (C4 (Web Text))

Max Activating Token Index: 692

Text #15

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7270. Min Act: 0.0000

Data Index: 783335 (C4 (Web Text))

Max Activating Token Index: 213

Text #16

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7211. Min Act: -0.0000

Data Index: 428702 (C4 (Web Text))

Max Activating Token Index: 677

Text #17

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7053. Min Act: -0.0000

Data Index: 1020014 (C4 (Web Text))

Max Activating Token Index: 923

Text #18

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.6810. Min Act: -0.0000

Data Index: 268475 (C4 (Web Text))

Max Activating Token Index: 835

Text #19

Max Range: 0.8945. Min Range: -0.8945

Max Act: 0.7248. Min Act: -0.0000

Data Index: 430858 (C4 (Web Text))

Max Activating Token Index: 904