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

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

Neuron 2753 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.2727. Min Act: -0.0000

Data Index: 727460 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.2536. Min Act: -0.0000

Data Index: 654913 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0863. Min Act: -0.0000

Data Index: 427226 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0596. Min Act: -0.0000

Data Index: 738013 (C4 (Web Text))

Max Activating Token Index: 651

Text #4

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.1244. Min Act: -0.0000

Data Index: 640152 (C4 (Web Text))

Max Activating Token Index: 845

Text #5

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0722. Min Act: -0.0000

Data Index: 157474 (C4 (Web Text))

Max Activating Token Index: 977

Text #6

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0231. Min Act: -0.0000

Data Index: 1198775 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0148. Min Act: -0.0000

Data Index: 554152 (C4 (Web Text))

Max Activating Token Index: 750

Text #8

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.9946. Min Act: -0.0000

Data Index: 576573 (C4 (Web Text))

Max Activating Token Index: 559

Text #9

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.9995. Min Act: -0.0000

Data Index: 1141773 (C4 (Web Text))

Max Activating Token Index: 567

Text #10

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0033. Min Act: -0.0000

Data Index: 411105 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0058. Min Act: -0.0000

Data Index: 912862 (C4 (Web Text))

Max Activating Token Index: 133

Text #12

Max Range: 1.2727. Min Range: -1.2727

Max Act: 1.0545. Min Act: -0.0000

Data Index: 1279388 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.9316. Min Act: -0.0000

Data Index: 584264 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.9691. Min Act: -0.0000

Data Index: 584612 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.9300. Min Act: -0.0000

Data Index: 737562 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.9562. Min Act: -0.0000

Data Index: 535293 (C4 (Web Text))

Max Activating Token Index: 196

Text #17

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.8295. Min Act: -0.0000

Data Index: 334021 (C4 (Web Text))

Max Activating Token Index: 841

Text #18

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.8611. Min Act: -0.0000

Data Index: 677196 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 1.2727. Min Range: -1.2727

Max Act: 0.8382. Min Act: -0.0000

Data Index: 201770 (C4 (Web Text))

Max Activating Token Index: 435