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

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

Neuron 2492 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: 3.9686. Min Range: -3.9686

Max Act: 3.9686. Min Act: -0.0001

Data Index: 691968 (C4 (Web Text))

Max Activating Token Index: 580

Text #1

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.8199. Min Act: -0.0001

Data Index: 758482 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.7768. Min Act: -0.0001

Data Index: 321838 (C4 (Web Text))

Max Activating Token Index: 738

Text #3

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.5052. Min Act: -0.0001

Data Index: 1355806 (C4 (Web Text))

Max Activating Token Index: 300

Text #4

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.3643. Min Act: -0.0001

Data Index: 1012010 (C4 (Web Text))

Max Activating Token Index: 151

Text #5

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.2673. Min Act: -0.0001

Data Index: 93835 (C4 (Web Text))

Max Activating Token Index: 333

Text #6

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.2430. Min Act: -0.0001

Data Index: 969522 (C4 (Web Text))

Max Activating Token Index: 411

Text #7

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.1590. Min Act: -0.0001

Data Index: 132557 (C4 (Web Text))

Max Activating Token Index: 892

Text #8

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.0187. Min Act: -0.0001

Data Index: 307348 (C4 (Web Text))

Max Activating Token Index: 953

Text #9

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.1381. Min Act: -0.0001

Data Index: 890538 (C4 (Web Text))

Max Activating Token Index: 780

Text #10

Max Range: 3.9686. Min Range: -3.9686

Max Act: 3.3513. Min Act: -0.0001

Data Index: 572062 (C4 (Web Text))

Max Activating Token Index: 713

Text #11

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.9545. Min Act: -0.0001

Data Index: 521646 (C4 (Web Text))

Max Activating Token Index: 1020

Text #12

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.9491. Min Act: -0.0001

Data Index: 583505 (C4 (Web Text))

Max Activating Token Index: 511

Text #13

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.9989. Min Act: -0.0001

Data Index: 510658 (C4 (Web Text))

Max Activating Token Index: 542

Text #14

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.8502. Min Act: -0.0001

Data Index: 1027773 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.9164. Min Act: -0.0001

Data Index: 352853 (C4 (Web Text))

Max Activating Token Index: 673

Text #16

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.8821. Min Act: -0.0001

Data Index: 1005504 (C4 (Web Text))

Max Activating Token Index: 302

Text #17

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.8280. Min Act: -0.0001

Data Index: 93232 (C4 (Web Text))

Max Activating Token Index: 449

Text #18

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.5534. Min Act: -0.0001

Data Index: 324298 (C4 (Web Text))

Max Activating Token Index: 386

Text #19

Max Range: 3.9686. Min Range: -3.9686

Max Act: 2.8930. Min Act: -0.0001

Data Index: 385884 (C4 (Web Text))

Max Activating Token Index: 366