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

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

Neuron 613 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: 1.5352. Min Range: -1.5352

Max Act: 1.5352. Min Act: -0.0001

Data Index: 1054742 (C4 (Web Text))

Max Activating Token Index: 519

Text #1

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.3712. Min Act: -0.0001

Data Index: 1037461 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.3626. Min Act: -0.0001

Data Index: 21282 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.3623. Min Act: -0.0001

Data Index: 1167221 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.3715. Min Act: -0.0001

Data Index: 1058095 (C4 (Web Text))

Max Activating Token Index: 190

Text #5

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.3728. Min Act: -0.0001

Data Index: 1072812 (C4 (Web Text))

Max Activating Token Index: 957

Text #6

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2467. Min Act: -0.0001

Data Index: 29126 (C4 (Web Text))

Max Activating Token Index: 201

Text #7

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2801. Min Act: -0.0001

Data Index: 202417 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.3208. Min Act: -0.0001

Data Index: 143234 (C4 (Web Text))

Max Activating Token Index: 1012

Text #9

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2328. Min Act: -0.0001

Data Index: 383645 (C4 (Web Text))

Max Activating Token Index: 58

Text #10

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2775. Min Act: -0.0001

Data Index: 259732 (C4 (Web Text))

Max Activating Token Index: 898

Text #11

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2389. Min Act: -0.0001

Data Index: 520107 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.1732. Min Act: -0.0001

Data Index: 551482 (C4 (Web Text))

Max Activating Token Index: 766

Text #13

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2343. Min Act: -0.0001

Data Index: 1194530 (C4 (Web Text))

Max Activating Token Index: 746

Text #14

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2323. Min Act: -0.0001

Data Index: 1029840 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.1947. Min Act: -0.0001

Data Index: 874550 (C4 (Web Text))

Max Activating Token Index: 80

Text #16

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.0581. Min Act: -0.0001

Data Index: 177752 (C4 (Web Text))

Max Activating Token Index: 753

Text #17

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.1394. Min Act: -0.0001

Data Index: 172920 (C4 (Web Text))

Max Activating Token Index: 862

Text #18

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.1845. Min Act: -0.0001

Data Index: 341055 (C4 (Web Text))

Max Activating Token Index: 74

Text #19

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2440. Min Act: -0.0001

Data Index: 383189 (C4 (Web Text))

Max Activating Token Index: 723