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

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

Neuron 1735 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.4945. Min Act: -0.0000

Data Index: 1288475 (C4 (Web Text))

Max Activating Token Index: 913

Text #1

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.4937. Min Act: -0.0000

Data Index: 515689 (C4 (Web Text))

Max Activating Token Index: 311

Text #2

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.4059. Min Act: -0.0000

Data Index: 1072479 (C4 (Web Text))

Max Activating Token Index: 86

Text #3

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.4282. Min Act: -0.0000

Data Index: 398546 (C4 (Web Text))

Max Activating Token Index: 630

Text #4

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3877. Min Act: -0.0000

Data Index: 344886 (C4 (Web Text))

Max Activating Token Index: 866

Text #5

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1091379 (C4 (Web Text))

Max Activating Token Index: 473

Text #6

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3929. Min Act: -0.0000

Data Index: 549610 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3906. Min Act: -0.0000

Data Index: 1305409 (C4 (Web Text))

Max Activating Token Index: 412

Text #8

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3884. Min Act: -0.0000

Data Index: 729366 (C4 (Web Text))

Max Activating Token Index: 960

Text #9

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3760. Min Act: -0.0000

Data Index: 1348848 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3773. Min Act: -0.0000

Data Index: 1025973 (C4 (Web Text))

Max Activating Token Index: 1008

Text #11

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3704. Min Act: -0.0000

Data Index: 383738 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3870. Min Act: -0.0000

Data Index: 356068 (C4 (Web Text))

Max Activating Token Index: 149

Text #13

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3482. Min Act: -0.0000

Data Index: 911062 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3456. Min Act: -0.0000

Data Index: 196764 (C4 (Web Text))

Max Activating Token Index: 298

Text #15

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3536. Min Act: -0.0000

Data Index: 824469 (C4 (Web Text))

Max Activating Token Index: 237

Text #16

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3623. Min Act: -0.0000

Data Index: 1337378 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3517. Min Act: -0.0000

Data Index: 372586 (C4 (Web Text))

Max Activating Token Index: 74

Text #18

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3615. Min Act: -0.0000

Data Index: 499088 (C4 (Web Text))

Max Activating Token Index: 1008

Text #19

Max Range: 0.4945. Min Range: -0.4945

Max Act: 0.3363. Min Act: -0.0000

Data Index: 352702 (C4 (Web Text))

Max Activating Token Index: 293