Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1269 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.9451. Min Act: -0.0000

Data Index: 341553 (C4 (Web Text))

Max Activating Token Index: 813

Text #1

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7660. Min Act: -0.0000

Data Index: 82039 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7722. Min Act: -0.0000

Data Index: 924511 (C4 (Web Text))

Max Activating Token Index: 910

Text #3

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.7320. Min Act: -0.0000

Data Index: 1032190 (C4 (Web Text))

Max Activating Token Index: 568

Text #4

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6791. Min Act: -0.0000

Data Index: 913880 (C4 (Web Text))

Max Activating Token Index: 126

Text #5

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6781. Min Act: -0.0000

Data Index: 579984 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6628. Min Act: -0.0000

Data Index: 762240 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6720. Min Act: -0.0000

Data Index: 467006 (C4 (Web Text))

Max Activating Token Index: 982

Text #8

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1302939 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1237134 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1190070 (C4 (Web Text))

Max Activating Token Index: 80

Text #11

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6779. Min Act: -0.0000

Data Index: 583973 (C4 (Web Text))

Max Activating Token Index: 596

Text #12

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6152. Min Act: -0.0000

Data Index: 33955 (C4 (Web Text))

Max Activating Token Index: 83

Text #13

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1043693 (C4 (Web Text))

Max Activating Token Index: 699

Text #14

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.5773. Min Act: -0.0000

Data Index: 349002 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.6134. Min Act: -0.0000

Data Index: 732678 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.5807. Min Act: -0.0000

Data Index: 93078 (C4 (Web Text))

Max Activating Token Index: 293

Text #17

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.5923. Min Act: -0.0000

Data Index: 32703 (C4 (Web Text))

Max Activating Token Index: 786

Text #18

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.5765. Min Act: -0.0000

Data Index: 463153 (C4 (Web Text))

Max Activating Token Index: 662

Text #19

Max Range: 0.9451. Min Range: -0.9451

Max Act: 0.5990. Min Act: -0.0000

Data Index: 595980 (C4 (Web Text))

Max Activating Token Index: 671