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

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

Neuron 526 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.1230. Min Act: -0.0000

Data Index: 136662 (C4 (Web Text))

Max Activating Token Index: 1015

Text #1

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.1923. Min Act: -0.0000

Data Index: 46050 (C4 (Web Text))

Max Activating Token Index: 494

Text #2

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.2511. Min Act: -0.0000

Data Index: 1058106 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0151. Min Act: -0.0000

Data Index: 445784 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0720. Min Act: -0.0000

Data Index: 574192 (C4 (Web Text))

Max Activating Token Index: 146

Text #5

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0645. Min Act: -0.0000

Data Index: 101050 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.1040. Min Act: -0.0000

Data Index: 926124 (C4 (Web Text))

Max Activating Token Index: 128

Text #7

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0349. Min Act: -0.0000

Data Index: 561565 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0435. Min Act: -0.0000

Data Index: 746648 (C4 (Web Text))

Max Activating Token Index: 929

Text #9

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0248. Min Act: -0.0000

Data Index: 825511 (C4 (Web Text))

Max Activating Token Index: 748

Text #10

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9963. Min Act: -0.0000

Data Index: 1180773 (C4 (Web Text))

Max Activating Token Index: 702

Text #11

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9892. Min Act: -0.0000

Data Index: 778037 (C4 (Web Text))

Max Activating Token Index: 746

Text #12

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9864. Min Act: -0.0000

Data Index: 814887 (C4 (Web Text))

Max Activating Token Index: 850

Text #13

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9217. Min Act: -0.0000

Data Index: 133087 (C4 (Web Text))

Max Activating Token Index: 1004

Text #14

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9621. Min Act: -0.0000

Data Index: 59130 (C4 (Web Text))

Max Activating Token Index: 989

Text #15

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9701. Min Act: -0.0000

Data Index: 1000764 (C4 (Web Text))

Max Activating Token Index: 804

Text #16

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9496. Min Act: -0.0000

Data Index: 514161 (C4 (Web Text))

Max Activating Token Index: 36

Text #17

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.8914. Min Act: -0.0000

Data Index: 627962 (C4 (Web Text))

Max Activating Token Index: 498

Text #18

Max Range: 1.2511. Min Range: -1.2511

Max Act: 0.9412. Min Act: -0.0000

Data Index: 92278 (C4 (Web Text))

Max Activating Token Index: 913

Text #19

Max Range: 1.2511. Min Range: -1.2511

Max Act: 1.0094. Min Act: -0.0000

Data Index: 355712 (C4 (Web Text))

Max Activating Token Index: 217