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

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

Neuron 5219 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.4539. Min Range: -3.4539

Max Act: 3.4539. Min Act: -0.0000

Data Index: 887564 (C4 (Web Text))

Max Activating Token Index: 682

Text #1

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.9676. Min Act: -0.0000

Data Index: 273844 (C4 (Web Text))

Max Activating Token Index: 510

Text #2

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.6473. Min Act: -0.0000

Data Index: 1036107 (C4 (Web Text))

Max Activating Token Index: 861

Text #3

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.4355. Min Act: -0.0000

Data Index: 1046741 (C4 (Web Text))

Max Activating Token Index: 469

Text #4

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.6976. Min Act: -0.0000

Data Index: 74408 (C4 (Web Text))

Max Activating Token Index: 739

Text #5

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.3496. Min Act: -0.0000

Data Index: 664268 (C4 (Web Text))

Max Activating Token Index: 537

Text #6

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.7052. Min Act: -0.0000

Data Index: 1158294 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.5253. Min Act: -0.0000

Data Index: 709812 (C4 (Web Text))

Max Activating Token Index: 802

Text #8

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.6354. Min Act: -0.0000

Data Index: 153002 (C4 (Web Text))

Max Activating Token Index: 729

Text #9

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.3032. Min Act: -0.0000

Data Index: 131346 (C4 (Web Text))

Max Activating Token Index: 140

Text #10

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.4167. Min Act: -0.0000

Data Index: 1207580 (C4 (Web Text))

Max Activating Token Index: 720

Text #11

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.6033. Min Act: -0.0000

Data Index: 29918 (C4 (Web Text))

Max Activating Token Index: 872

Text #12

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.4221. Min Act: -0.0000

Data Index: 667587 (C4 (Web Text))

Max Activating Token Index: 765

Text #13

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.3078. Min Act: -0.0000

Data Index: 692504 (C4 (Web Text))

Max Activating Token Index: 382

Text #14

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.1816. Min Act: -0.0000

Data Index: 501444 (C4 (Web Text))

Max Activating Token Index: 688

Text #15

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.1962. Min Act: -0.0000

Data Index: 206191 (C4 (Web Text))

Max Activating Token Index: 976

Text #16

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.3931. Min Act: -0.0000

Data Index: 626362 (C4 (Web Text))

Max Activating Token Index: 77

Text #17

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.0390. Min Act: -0.0000

Data Index: 148070 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.4458. Min Act: -0.0000

Data Index: 82580 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 3.4539. Min Range: -3.4539

Max Act: 2.4436. Min Act: -0.0000

Data Index: 698704 (C4 (Web Text))

Max Activating Token Index: 825