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

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

Neuron 1059 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7687. Min Act: -0.0002

Data Index: 509195 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8540. Min Act: -0.0001

Data Index: 624800 (C4 (Web Text))

Max Activating Token Index: 196

Text #2

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7750. Min Act: -0.0001

Data Index: 185081 (C4 (Web Text))

Max Activating Token Index: 641

Text #3

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7756. Min Act: -0.0001

Data Index: 763391 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.8186. Min Act: -0.0001

Data Index: 731107 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7636. Min Act: -0.0002

Data Index: 1281757 (C4 (Web Text))

Max Activating Token Index: 879

Text #6

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7429. Min Act: -0.0002

Data Index: 985837 (C4 (Web Text))

Max Activating Token Index: 112

Text #7

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6974. Min Act: -0.0002

Data Index: 812994 (C4 (Web Text))

Max Activating Token Index: 10

Text #8

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6647. Min Act: -0.0001

Data Index: 1225087 (C4 (Web Text))

Max Activating Token Index: 816

Text #9

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6755. Min Act: -0.0002

Data Index: 667563 (C4 (Web Text))

Max Activating Token Index: 126

Text #10

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6933. Min Act: -0.0002

Data Index: 108209 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6775. Min Act: -0.0001

Data Index: 577990 (C4 (Web Text))

Max Activating Token Index: 289

Text #12

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6573. Min Act: -0.0002

Data Index: 39310 (C4 (Web Text))

Max Activating Token Index: 638

Text #13

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.7156. Min Act: -0.0002

Data Index: 755459 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6266. Min Act: -0.0002

Data Index: 762573 (C4 (Web Text))

Max Activating Token Index: 779

Text #15

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6485. Min Act: -0.0002

Data Index: 100946 (C4 (Web Text))

Max Activating Token Index: 619

Text #16

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6810. Min Act: -0.0002

Data Index: 445483 (C4 (Web Text))

Max Activating Token Index: 804

Text #17

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6651. Min Act: -0.0002

Data Index: 389592 (C4 (Web Text))

Max Activating Token Index: 233

Text #18

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6539. Min Act: -0.0001

Data Index: 279310 (C4 (Web Text))

Max Activating Token Index: 296

Text #19

Max Range: 0.8540. Min Range: -0.8540

Max Act: 0.6101. Min Act: -0.0002

Data Index: 770392 (C4 (Web Text))

Max Activating Token Index: 31