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

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

Neuron 1587 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: 0.1474. Min Range: -0.1474

Max Act: 0.1474. Min Act: -0.0000

Data Index: 890361 (C4 (Web Text))

Max Activating Token Index: 745

Text #1

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1048. Min Act: -0.0000

Data Index: 313532 (C4 (Web Text))

Max Activating Token Index: 236

Text #2

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1002. Min Act: -0.0000

Data Index: 51464 (C4 (Web Text))

Max Activating Token Index: 731

Text #3

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.1037. Min Act: -0.0000

Data Index: 754405 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0945. Min Act: -0.0000

Data Index: 445256 (C4 (Web Text))

Max Activating Token Index: 443

Text #5

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0942. Min Act: -0.0000

Data Index: 810464 (C4 (Web Text))

Max Activating Token Index: 748

Text #6

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0919. Min Act: -0.0000

Data Index: 1173065 (C4 (Web Text))

Max Activating Token Index: 712

Text #7

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1203998 (C4 (Web Text))

Max Activating Token Index: 255

Text #8

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0870. Min Act: -0.0000

Data Index: 586794 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0866. Min Act: -0.0000

Data Index: 973718 (C4 (Web Text))

Max Activating Token Index: 607

Text #10

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0888. Min Act: -0.0000

Data Index: 322332 (C4 (Web Text))

Max Activating Token Index: 692

Text #11

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0880. Min Act: -0.0000

Data Index: 641216 (C4 (Web Text))

Max Activating Token Index: 547

Text #12

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0882. Min Act: -0.0000

Data Index: 280601 (C4 (Web Text))

Max Activating Token Index: 592

Text #13

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0874. Min Act: -0.0000

Data Index: 360062 (C4 (Web Text))

Max Activating Token Index: 922

Text #14

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0906. Min Act: -0.0000

Data Index: 389244 (C4 (Web Text))

Max Activating Token Index: 346

Text #15

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1174307 (C4 (Web Text))

Max Activating Token Index: 296

Text #16

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0864. Min Act: -0.0000

Data Index: 712217 (C4 (Web Text))

Max Activating Token Index: 122

Text #17

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1038129 (C4 (Web Text))

Max Activating Token Index: 177

Text #18

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0850. Min Act: -0.0000

Data Index: 142367 (C4 (Web Text))

Max Activating Token Index: 576

Text #19

Max Range: 0.1474. Min Range: -0.1474

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1231149 (C4 (Web Text))

Max Activating Token Index: 271