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

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

Neuron 769 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.5147. Min Act: -0.0000

Data Index: 687454 (C4 (Web Text))

Max Activating Token Index: 664

Text #1

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.5286. Min Act: -0.0000

Data Index: 450402 (C4 (Web Text))

Max Activating Token Index: 683

Text #2

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4732. Min Act: -0.0001

Data Index: 1065069 (C4 (Web Text))

Max Activating Token Index: 891

Text #3

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4349. Min Act: -0.0000

Data Index: 873065 (C4 (Web Text))

Max Activating Token Index: 33

Text #4

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4041. Min Act: -0.0000

Data Index: 978126 (C4 (Web Text))

Max Activating Token Index: 525

Text #5

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4094. Min Act: -0.0001

Data Index: 1097193 (C4 (Web Text))

Max Activating Token Index: 939

Text #6

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3923. Min Act: -0.0001

Data Index: 1341139 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3918. Min Act: -0.0000

Data Index: 125314 (C4 (Web Text))

Max Activating Token Index: 880

Text #8

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3812. Min Act: -0.0000

Data Index: 223161 (C4 (Web Text))

Max Activating Token Index: 272

Text #9

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3900. Min Act: -0.0001

Data Index: 1356395 (C4 (Web Text))

Max Activating Token Index: 214

Text #10

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.4016. Min Act: -0.0001

Data Index: 512476 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3381. Min Act: -0.0001

Data Index: 335664 (C4 (Web Text))

Max Activating Token Index: 567

Text #12

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3830. Min Act: -0.0000

Data Index: 227299 (C4 (Web Text))

Max Activating Token Index: 994

Text #13

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3953. Min Act: -0.0000

Data Index: 1126714 (C4 (Web Text))

Max Activating Token Index: 948

Text #14

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3760. Min Act: -0.0001

Data Index: 284950 (C4 (Web Text))

Max Activating Token Index: 102

Text #15

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3606. Min Act: -0.0000

Data Index: 179502 (C4 (Web Text))

Max Activating Token Index: 743

Text #16

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3674. Min Act: -0.0000

Data Index: 539820 (C4 (Web Text))

Max Activating Token Index: 413

Text #17

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3403. Min Act: -0.0000

Data Index: 934054 (C4 (Web Text))

Max Activating Token Index: 591

Text #18

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3741. Min Act: -0.0000

Data Index: 1211664 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 0.5286. Min Range: -0.5286

Max Act: 0.3722. Min Act: -0.0001

Data Index: 843458 (C4 (Web Text))

Max Activating Token Index: 102