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

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

Neuron 3013 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: 0.4854. Min Range: -0.4854

Max Act: 0.4854. Min Act: -0.0000

Data Index: 246371 (C4 (Web Text))

Max Activating Token Index: 713

Text #1

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4647. Min Act: -0.0000

Data Index: 983106 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4568. Min Act: -0.0000

Data Index: 373084 (C4 (Web Text))

Max Activating Token Index: 126

Text #3

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4469. Min Act: -0.0000

Data Index: 335075 (C4 (Web Text))

Max Activating Token Index: 983

Text #4

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4299. Min Act: -0.0001

Data Index: 1129255 (C4 (Web Text))

Max Activating Token Index: 623

Text #5

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4448. Min Act: -0.0001

Data Index: 1006860 (C4 (Web Text))

Max Activating Token Index: 427

Text #6

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4363. Min Act: -0.0001

Data Index: 137187 (C4 (Web Text))

Max Activating Token Index: 436

Text #7

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4237. Min Act: -0.0000

Data Index: 383255 (C4 (Web Text))

Max Activating Token Index: 339

Text #8

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3946. Min Act: -0.0000

Data Index: 270456 (C4 (Web Text))

Max Activating Token Index: 695

Text #9

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.4022. Min Act: -0.0000

Data Index: 1175847 (C4 (Web Text))

Max Activating Token Index: 915

Text #10

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3961. Min Act: -0.0001

Data Index: 1122059 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3614. Min Act: -0.0000

Data Index: 842041 (C4 (Web Text))

Max Activating Token Index: 691

Text #12

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3914. Min Act: -0.0000

Data Index: 160878 (C4 (Web Text))

Max Activating Token Index: 393

Text #13

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3879. Min Act: -0.0000

Data Index: 624293 (C4 (Web Text))

Max Activating Token Index: 953

Text #14

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3612. Min Act: -0.0000

Data Index: 777482 (C4 (Web Text))

Max Activating Token Index: 628

Text #15

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3802. Min Act: -0.0000

Data Index: 652576 (C4 (Web Text))

Max Activating Token Index: 886

Text #16

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3600. Min Act: -0.0001

Data Index: 484151 (C4 (Web Text))

Max Activating Token Index: 569

Text #17

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3689. Min Act: -0.0000

Data Index: 1118492 (C4 (Web Text))

Max Activating Token Index: 303

Text #18

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3757. Min Act: -0.0000

Data Index: 1126283 (C4 (Web Text))

Max Activating Token Index: 626

Text #19

Max Range: 0.4854. Min Range: -0.4854

Max Act: 0.3514. Min Act: -0.0000

Data Index: 804387 (C4 (Web Text))

Max Activating Token Index: 673