Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 2042 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.4248. Min Range: -6.4248

Max Act: 6.4248. Min Act: -0.0000

Data Index: 352406 (C4 (Web Text))

Max Activating Token Index: 546

Text #1

Max Range: 6.4248. Min Range: -6.4248

Max Act: 6.1052. Min Act: -0.0000

Data Index: 1150633 (C4 (Web Text))

Max Activating Token Index: 358

Text #2

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.8789. Min Act: -0.0000

Data Index: 768382 (C4 (Web Text))

Max Activating Token Index: 667

Text #3

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.4510. Min Act: -0.0000

Data Index: 939971 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.5862. Min Act: -0.0000

Data Index: 1307526 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.2018. Min Act: -0.0000

Data Index: 359029 (C4 (Web Text))

Max Activating Token Index: 132

Text #6

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.6784. Min Act: -0.0000

Data Index: 769972 (C4 (Web Text))

Max Activating Token Index: 278

Text #7

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.0633. Min Act: -0.0000

Data Index: 461312 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.1606. Min Act: -0.0000

Data Index: 1262754 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.0266. Min Act: -0.0000

Data Index: 1582500 (Python Code)

Max Activating Token Index: 298

Text #10

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.1950. Min Act: -0.0000

Data Index: 12637 (C4 (Web Text))

Max Activating Token Index: 829

Text #11

Max Range: 6.4248. Min Range: -6.4248

Max Act: 4.9539. Min Act: -0.0000

Data Index: 1152717 (C4 (Web Text))

Max Activating Token Index: 391

Text #12

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.1130. Min Act: -0.0000

Data Index: 505416 (C4 (Web Text))

Max Activating Token Index: 575

Text #13

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.1169. Min Act: -0.0000

Data Index: 785174 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.0873. Min Act: -0.0000

Data Index: 467985 (C4 (Web Text))

Max Activating Token Index: 801

Text #15

Max Range: 6.4248. Min Range: -6.4248

Max Act: 4.6436. Min Act: -0.0000

Data Index: 798396 (C4 (Web Text))

Max Activating Token Index: 982

Text #16

Max Range: 6.4248. Min Range: -6.4248

Max Act: 4.8134. Min Act: -0.0000

Data Index: 531688 (C4 (Web Text))

Max Activating Token Index: 506

Text #17

Max Range: 6.4248. Min Range: -6.4248

Max Act: 4.9751. Min Act: -0.0000

Data Index: 479222 (C4 (Web Text))

Max Activating Token Index: 476

Text #18

Max Range: 6.4248. Min Range: -6.4248

Max Act: 4.7952. Min Act: -0.0000

Data Index: 1114796 (C4 (Web Text))

Max Activating Token Index: 404

Text #19

Max Range: 6.4248. Min Range: -6.4248

Max Act: 5.1434. Min Act: -0.0000

Data Index: 349838 (C4 (Web Text))

Max Activating Token Index: 450