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

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

Neuron 376 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1587. Min Range: -2.1587

Max Act: 2.1587. Min Act: -0.0001

Data Index: 396832 (C4 (Web Text))

Max Activating Token Index: 488

Text #1

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.9112. Min Act: -0.0000

Data Index: 1604022 (Python Code)

Max Activating Token Index: 733

Text #2

Max Range: 2.1587. Min Range: -2.1587

Max Act: 2.0381. Min Act: -0.0000

Data Index: 771370 (C4 (Web Text))

Max Activating Token Index: 762

Text #3

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.9886. Min Act: -0.0000

Data Index: 1417539 (Python Code)

Max Activating Token Index: 511

Text #4

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.7205. Min Act: -0.0000

Data Index: 53886 (C4 (Web Text))

Max Activating Token Index: 979

Text #5

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.7261. Min Act: -0.0000

Data Index: 1583931 (Python Code)

Max Activating Token Index: 22

Text #6

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.4505. Min Act: -0.0000

Data Index: 627413 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.4578. Min Act: -0.0000

Data Index: 1479391 (Python Code)

Max Activating Token Index: 728

Text #8

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.5213. Min Act: -0.0000

Data Index: 1564501 (Python Code)

Max Activating Token Index: 775

Text #9

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.6806. Min Act: -0.0000

Data Index: 793690 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.6829. Min Act: -0.0000

Data Index: 1652954 (Python Code)

Max Activating Token Index: 727

Text #11

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.5829. Min Act: -0.0000

Data Index: 694112 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.6310. Min Act: -0.0000

Data Index: 1525285 (Python Code)

Max Activating Token Index: 69

Text #13

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.5288. Min Act: -0.0000

Data Index: 1474460 (Python Code)

Max Activating Token Index: 859

Text #14

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.6260. Min Act: -0.0000

Data Index: 1463620 (Python Code)

Max Activating Token Index: 100

Text #15

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.4269. Min Act: -0.0000

Data Index: 854736 (C4 (Web Text))

Max Activating Token Index: 510

Text #16

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.4143. Min Act: -0.0000

Data Index: 1568078 (Python Code)

Max Activating Token Index: 261

Text #17

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.3812. Min Act: -0.0000

Data Index: 1176761 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.4566. Min Act: -0.0000

Data Index: 634611 (C4 (Web Text))

Max Activating Token Index: 491

Text #19

Max Range: 2.1587. Min Range: -2.1587

Max Act: 1.3913. Min Act: -0.0000

Data Index: 1426508 (Python Code)

Max Activating Token Index: 486