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

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

Neuron 558 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: 2.4981. Min Range: -2.4981

Max Act: 2.4981. Min Act: -0.0000

Data Index: 1342583 (C4 (Web Text))

Max Activating Token Index: 707

Text #1

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.4172. Min Act: -0.0000

Data Index: 1337080 (C4 (Web Text))

Max Activating Token Index: 594

Text #2

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.2689. Min Act: -0.0000

Data Index: 1047310 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.2585. Min Act: -0.0000

Data Index: 527847 (C4 (Web Text))

Max Activating Token Index: 466

Text #4

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.3388. Min Act: -0.0000

Data Index: 1505487 (Python Code)

Max Activating Token Index: 537

Text #5

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.1884. Min Act: -0.0000

Data Index: 1269544 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.1755. Min Act: -0.0000

Data Index: 149446 (C4 (Web Text))

Max Activating Token Index: 494

Text #7

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.2887. Min Act: -0.0000

Data Index: 1446892 (Python Code)

Max Activating Token Index: 544

Text #8

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.2398. Min Act: -0.0000

Data Index: 860805 (C4 (Web Text))

Max Activating Token Index: 613

Text #9

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.2228. Min Act: -0.0000

Data Index: 1501117 (Python Code)

Max Activating Token Index: 327

Text #10

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.1984. Min Act: -0.0000

Data Index: 1602523 (Python Code)

Max Activating Token Index: 999

Text #11

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.1994. Min Act: -0.0000

Data Index: 1626108 (Python Code)

Max Activating Token Index: 382

Text #12

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.3095. Min Act: -0.0000

Data Index: 792420 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.0575. Min Act: -0.0000

Data Index: 284333 (C4 (Web Text))

Max Activating Token Index: 324

Text #14

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.1769. Min Act: -0.0000

Data Index: 1548821 (Python Code)

Max Activating Token Index: 411

Text #15

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.4026. Min Act: -0.0000

Data Index: 22680 (C4 (Web Text))

Max Activating Token Index: 223

Text #16

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.2889. Min Act: -0.0000

Data Index: 201625 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.2323. Min Act: -0.0000

Data Index: 1126532 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.1044. Min Act: -0.0000

Data Index: 1430734 (Python Code)

Max Activating Token Index: 91

Text #19

Max Range: 2.4981. Min Range: -2.4981

Max Act: 2.0858. Min Act: -0.0000

Data Index: 750286 (C4 (Web Text))

Max Activating Token Index: 535