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

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

Neuron 894 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.8666. Min Act: -0.0000

Data Index: 596133 (C4 (Web Text))

Max Activating Token Index: 469

Text #1

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.8358. Min Act: -0.0000

Data Index: 615674 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.7292. Min Act: -0.0000

Data Index: 751969 (C4 (Web Text))

Max Activating Token Index: 149

Text #3

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.4263. Min Act: -0.0000

Data Index: 476298 (C4 (Web Text))

Max Activating Token Index: 155

Text #4

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.4115. Min Act: -0.0000

Data Index: 656987 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.3456. Min Act: -0.0000

Data Index: 971491 (C4 (Web Text))

Max Activating Token Index: 934

Text #6

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.4698. Min Act: -0.0000

Data Index: 749414 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.4592. Min Act: -0.0000

Data Index: 1143816 (C4 (Web Text))

Max Activating Token Index: 945

Text #8

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.2432. Min Act: -0.0000

Data Index: 620884 (C4 (Web Text))

Max Activating Token Index: 124

Text #9

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.2260. Min Act: -0.0000

Data Index: 994414 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.2221. Min Act: -0.0000

Data Index: 1344386 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.1843. Min Act: -0.0000

Data Index: 1065004 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.2740. Min Act: -0.0000

Data Index: 64145 (C4 (Web Text))

Max Activating Token Index: 774

Text #13

Max Range: 3.8666. Min Range: -3.8666

Max Act: 2.9789. Min Act: -0.0000

Data Index: 82662 (C4 (Web Text))

Max Activating Token Index: 881

Text #14

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.0453. Min Act: -0.0000

Data Index: 675416 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.0508. Min Act: -0.0000

Data Index: 1195042 (C4 (Web Text))

Max Activating Token Index: 101

Text #16

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.0341. Min Act: -0.0000

Data Index: 478832 (C4 (Web Text))

Max Activating Token Index: 617

Text #17

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.1501. Min Act: -0.0000

Data Index: 854881 (C4 (Web Text))

Max Activating Token Index: 925

Text #18

Max Range: 3.8666. Min Range: -3.8666

Max Act: 3.0085. Min Act: -0.0000

Data Index: 1242268 (C4 (Web Text))

Max Activating Token Index: 178

Text #19

Max Range: 3.8666. Min Range: -3.8666

Max Act: 2.9754. Min Act: -0.0000

Data Index: 868551 (C4 (Web Text))

Max Activating Token Index: 137