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

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

Neuron 4545 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1480. Min Act: -0.0000

Data Index: 583536 (C4 (Web Text))

Max Activating Token Index: 397

Text #1

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1429. Min Act: -0.0000

Data Index: 634728 (C4 (Web Text))

Max Activating Token Index: 248

Text #2

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1214. Min Act: -0.0000

Data Index: 539318 (C4 (Web Text))

Max Activating Token Index: 1020

Text #3

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1108. Min Act: -0.0000

Data Index: 563312 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1027. Min Act: -0.0000

Data Index: 609112 (C4 (Web Text))

Max Activating Token Index: 910

Text #5

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1047. Min Act: -0.0000

Data Index: 1504521 (Python Code)

Max Activating Token Index: 301

Text #6

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1035. Min Act: -0.0000

Data Index: 357381 (C4 (Web Text))

Max Activating Token Index: 289

Text #7

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1103. Min Act: -0.0000

Data Index: 1305120 (C4 (Web Text))

Max Activating Token Index: 529

Text #8

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1055. Min Act: -0.0000

Data Index: 1321802 (C4 (Web Text))

Max Activating Token Index: 890

Text #9

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1060. Min Act: -0.0000

Data Index: 1011778 (C4 (Web Text))

Max Activating Token Index: 414

Text #10

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0980. Min Act: -0.0000

Data Index: 308809 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0890. Min Act: -0.0000

Data Index: 950620 (C4 (Web Text))

Max Activating Token Index: 865

Text #12

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1175943 (C4 (Web Text))

Max Activating Token Index: 96

Text #13

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1107. Min Act: -0.0000

Data Index: 342517 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.1142. Min Act: -0.0000

Data Index: 1031805 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0966. Min Act: -0.0000

Data Index: 229734 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0963. Min Act: -0.0000

Data Index: 939044 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0926. Min Act: -0.0000

Data Index: 1350163 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0841. Min Act: -0.0000

Data Index: 813359 (C4 (Web Text))

Max Activating Token Index: 375

Text #19

Max Range: 0.1480. Min Range: -0.1480

Max Act: 0.0885. Min Act: -0.0000

Data Index: 974737 (C4 (Web Text))

Max Activating Token Index: 635