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

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

Neuron 489 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1331. Min Range: -2.1331

Max Act: 2.1331. Min Act: -0.0000

Data Index: 254886 (C4 (Web Text))

Max Activating Token Index: 619

Text #1

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.7831. Min Act: -0.0000

Data Index: 1155025 (C4 (Web Text))

Max Activating Token Index: 449

Text #2

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.3665. Min Act: -0.0000

Data Index: 1467761 (Python Code)

Max Activating Token Index: 208

Text #3

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.5363. Min Act: -0.0000

Data Index: 1033865 (C4 (Web Text))

Max Activating Token Index: 599

Text #4

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.3933. Min Act: -0.0000

Data Index: 377226 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.5842. Min Act: -0.0000

Data Index: 1595716 (Python Code)

Max Activating Token Index: 796

Text #6

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.7314. Min Act: -0.0000

Data Index: 155836 (C4 (Web Text))

Max Activating Token Index: 923

Text #7

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.4594. Min Act: -0.0000

Data Index: 788921 (C4 (Web Text))

Max Activating Token Index: 249

Text #8

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.4186. Min Act: -0.0000

Data Index: 1304033 (C4 (Web Text))

Max Activating Token Index: 268

Text #9

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.4563. Min Act: -0.0000

Data Index: 1372839 (Python Code)

Max Activating Token Index: 864

Text #10

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.2894. Min Act: -0.0000

Data Index: 428560 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.2492. Min Act: -0.0000

Data Index: 1144810 (C4 (Web Text))

Max Activating Token Index: 964

Text #12

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.3199. Min Act: -0.0000

Data Index: 405045 (C4 (Web Text))

Max Activating Token Index: 283

Text #13

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.2681. Min Act: -0.0000

Data Index: 846091 (C4 (Web Text))

Max Activating Token Index: 554

Text #14

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.2801. Min Act: -0.0000

Data Index: 922982 (C4 (Web Text))

Max Activating Token Index: 398

Text #15

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.2069. Min Act: -0.0000

Data Index: 430945 (C4 (Web Text))

Max Activating Token Index: 88

Text #16

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.1997. Min Act: -0.0000

Data Index: 1475802 (Python Code)

Max Activating Token Index: 623

Text #17

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.1745. Min Act: -0.0000

Data Index: 406290 (C4 (Web Text))

Max Activating Token Index: 168

Text #18

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.1528. Min Act: -0.0000

Data Index: 755219 (C4 (Web Text))

Max Activating Token Index: 493

Text #19

Max Range: 2.1331. Min Range: -2.1331

Max Act: 1.1633. Min Act: -0.0000

Data Index: 1530657 (Python Code)

Max Activating Token Index: 308