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

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

Neuron 4934 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.6759. Min Act: -0.0000

Data Index: 455986 (C4 (Web Text))

Max Activating Token Index: 1005

Text #1

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.4627. Min Act: -0.0000

Data Index: 521384 (C4 (Web Text))

Max Activating Token Index: 581

Text #2

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.2270. Min Act: -0.0000

Data Index: 530193 (C4 (Web Text))

Max Activating Token Index: 881

Text #3

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.1962. Min Act: -0.0000

Data Index: 584667 (C4 (Web Text))

Max Activating Token Index: 327

Text #4

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.3022. Min Act: -0.0000

Data Index: 1177232 (C4 (Web Text))

Max Activating Token Index: 424

Text #5

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.1406. Min Act: -0.0000

Data Index: 628865 (C4 (Web Text))

Max Activating Token Index: 741

Text #6

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.0997. Min Act: -0.0000

Data Index: 1117509 (C4 (Web Text))

Max Activating Token Index: 607

Text #7

Max Range: 2.6759. Min Range: -2.6759

Max Act: 1.8222. Min Act: -0.0000

Data Index: 989714 (C4 (Web Text))

Max Activating Token Index: 234

Text #8

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.0329. Min Act: -0.0000

Data Index: 1251534 (C4 (Web Text))

Max Activating Token Index: 862

Text #9

Max Range: 2.6759. Min Range: -2.6759

Max Act: 1.8933. Min Act: -0.0000

Data Index: 164567 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.0060. Min Act: -0.0000

Data Index: 395253 (C4 (Web Text))

Max Activating Token Index: 102

Text #11

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.0891. Min Act: -0.0000

Data Index: 821147 (C4 (Web Text))

Max Activating Token Index: 916

Text #12

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.1816. Min Act: -0.0000

Data Index: 1071063 (C4 (Web Text))

Max Activating Token Index: 667

Text #13

Max Range: 2.6759. Min Range: -2.6759

Max Act: 1.8826. Min Act: -0.0000

Data Index: 474712 (C4 (Web Text))

Max Activating Token Index: 413

Text #14

Max Range: 2.6759. Min Range: -2.6759

Max Act: 2.0863. Min Act: -0.0000

Data Index: 1339909 (C4 (Web Text))

Max Activating Token Index: 555

Text #15

Max Range: 2.6759. Min Range: -2.6759

Max Act: 1.9456. Min Act: -0.0000

Data Index: 947252 (C4 (Web Text))

Max Activating Token Index: 788

Text #16

Max Range: 2.6759. Min Range: -2.6759

Max Act: 1.8547. Min Act: -0.0000

Data Index: 521381 (C4 (Web Text))

Max Activating Token Index: 280

Text #17

Max Range: 2.6759. Min Range: -2.6759

Max Act: 1.6340. Min Act: -0.0000

Data Index: 310127 (C4 (Web Text))

Max Activating Token Index: 834

Text #18

Max Range: 2.6759. Min Range: -2.6759

Max Act: 1.7916. Min Act: -0.0000

Data Index: 185937 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 2.6759. Min Range: -2.6759

Max Act: 1.8969. Min Act: -0.0000

Data Index: 1215798 (C4 (Web Text))

Max Activating Token Index: 453