Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4367 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6816. Min Act: -0.0000

Data Index: 1513139 (Python Code)

Max Activating Token Index: 956

Text #1

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.6779. Min Act: -0.0000

Data Index: 1420136 (Python Code)

Max Activating Token Index: 715

Text #2

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1478700 (Python Code)

Max Activating Token Index: 466

Text #3

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1527574 (Python Code)

Max Activating Token Index: 596

Text #4

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4541. Min Act: -0.0000

Data Index: 914300 (C4 (Web Text))

Max Activating Token Index: 606

Text #5

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4529. Min Act: -0.0000

Data Index: 795922 (C4 (Web Text))

Max Activating Token Index: 573

Text #6

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3978. Min Act: -0.0000

Data Index: 1094547 (C4 (Web Text))

Max Activating Token Index: 536

Text #7

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3928. Min Act: -0.0000

Data Index: 1181531 (C4 (Web Text))

Max Activating Token Index: 551

Text #8

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.4272. Min Act: -0.0000

Data Index: 414409 (C4 (Web Text))

Max Activating Token Index: 223

Text #9

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3944. Min Act: -0.0000

Data Index: 1399872 (Python Code)

Max Activating Token Index: 876

Text #10

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3618. Min Act: -0.0000

Data Index: 358781 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3662. Min Act: -0.0000

Data Index: 1484200 (Python Code)

Max Activating Token Index: 49

Text #12

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3613. Min Act: -0.0000

Data Index: 1263906 (C4 (Web Text))

Max Activating Token Index: 244

Text #13

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3387. Min Act: -0.0000

Data Index: 423453 (C4 (Web Text))

Max Activating Token Index: 1001

Text #14

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.2612. Min Act: -0.0000

Data Index: 1467201 (Python Code)

Max Activating Token Index: 523

Text #15

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3061. Min Act: -0.0000

Data Index: 686790 (C4 (Web Text))

Max Activating Token Index: 453

Text #16

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.3369. Min Act: -0.0000

Data Index: 1048043 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.2934. Min Act: -0.0000

Data Index: 1417984 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.2945. Min Act: -0.0000

Data Index: 708637 (C4 (Web Text))

Max Activating Token Index: 862

Text #19

Max Range: 0.6816. Min Range: -0.6816

Max Act: 0.2604. Min Act: -0.0000

Data Index: 185454 (C4 (Web Text))

Max Activating Token Index: 166