Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3235 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5736. Min Act: -0.0000

Data Index: 473417 (C4 (Web Text))

Max Activating Token Index: 576

Text #1

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.6265. Min Act: -0.0000

Data Index: 999176 (C4 (Web Text))

Max Activating Token Index: 323

Text #2

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5906. Min Act: -0.0000

Data Index: 938021 (C4 (Web Text))

Max Activating Token Index: 898

Text #3

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.6054. Min Act: -0.0000

Data Index: 1081146 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5803. Min Act: -0.0000

Data Index: 370523 (C4 (Web Text))

Max Activating Token Index: 412

Text #5

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5886. Min Act: -0.0000

Data Index: 231633 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5762. Min Act: -0.0000

Data Index: 695128 (C4 (Web Text))

Max Activating Token Index: 614

Text #7

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5638. Min Act: -0.0000

Data Index: 306505 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5461. Min Act: -0.0000

Data Index: 297321 (C4 (Web Text))

Max Activating Token Index: 952

Text #9

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5672. Min Act: -0.0000

Data Index: 75950 (C4 (Web Text))

Max Activating Token Index: 328

Text #10

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5701. Min Act: -0.0000

Data Index: 705739 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5382. Min Act: -0.0000

Data Index: 18280 (C4 (Web Text))

Max Activating Token Index: 779

Text #12

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5306. Min Act: -0.0000

Data Index: 580201 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5042. Min Act: -0.0000

Data Index: 698664 (C4 (Web Text))

Max Activating Token Index: 976

Text #14

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5145. Min Act: -0.0000

Data Index: 272427 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5345. Min Act: -0.0000

Data Index: 697359 (C4 (Web Text))

Max Activating Token Index: 369

Text #16

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5989. Min Act: -0.0000

Data Index: 518575 (C4 (Web Text))

Max Activating Token Index: 791

Text #17

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5101. Min Act: -0.0000

Data Index: 758641 (C4 (Web Text))

Max Activating Token Index: 583

Text #18

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5108. Min Act: -0.0000

Data Index: 1459800 (Python Code)

Max Activating Token Index: 511

Text #19

Max Range: 0.6265. Min Range: -0.6265

Max Act: 0.5111. Min Act: -0.0000

Data Index: 1208122 (C4 (Web Text))

Max Activating Token Index: 710