Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2300 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 5.1481. Min Range: -5.1481

Max Act: 5.1481. Min Act: -0.0001

Data Index: 509456 (C4 (Web Text))

Max Activating Token Index: 825

Text #1

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.9752. Min Act: -0.0001

Data Index: 918243 (C4 (Web Text))

Max Activating Token Index: 786

Text #2

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.6115. Min Act: -0.0001

Data Index: 180848 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.5232. Min Act: -0.0001

Data Index: 296884 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.1330. Min Act: -0.0001

Data Index: 49206 (C4 (Web Text))

Max Activating Token Index: 352

Text #5

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.2686. Min Act: -0.0001

Data Index: 163459 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.5080. Min Act: -0.0001

Data Index: 365636 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.1917. Min Act: -0.0001

Data Index: 647317 (C4 (Web Text))

Max Activating Token Index: 245

Text #8

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.1905. Min Act: -0.0001

Data Index: 658279 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.2837. Min Act: -0.0001

Data Index: 559089 (C4 (Web Text))

Max Activating Token Index: 711

Text #10

Max Range: 5.1481. Min Range: -5.1481

Max Act: 4.1335. Min Act: -0.0001

Data Index: 979607 (C4 (Web Text))

Max Activating Token Index: 48

Text #11

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.7638. Min Act: -0.0001

Data Index: 285414 (C4 (Web Text))

Max Activating Token Index: 896

Text #12

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.7858. Min Act: -0.0001

Data Index: 764041 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.6178. Min Act: -0.0001

Data Index: 566530 (C4 (Web Text))

Max Activating Token Index: 215

Text #14

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.3567. Min Act: -0.0001

Data Index: 243018 (C4 (Web Text))

Max Activating Token Index: 829

Text #15

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.3014. Min Act: -0.0001

Data Index: 961969 (C4 (Web Text))

Max Activating Token Index: 461

Text #16

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.5568. Min Act: -0.0001

Data Index: 4604 (C4 (Web Text))

Max Activating Token Index: 616

Text #17

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.5681. Min Act: -0.0001

Data Index: 33491 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.5117. Min Act: -0.0001

Data Index: 1205776 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 5.1481. Min Range: -5.1481

Max Act: 3.4438. Min Act: -0.0001

Data Index: 602221 (C4 (Web Text))

Max Activating Token Index: 370