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

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

Neuron 2328 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: 0.0797. Min Range: -0.0797

Max Act: 0.0797. Min Act: -0.0001

Data Index: 97348 (C4 (Web Text))

Max Activating Token Index: 993

Text #1

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0515. Min Act: -0.0001

Data Index: 987611 (C4 (Web Text))

Max Activating Token Index: 767

Text #2

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0536. Min Act: -0.0001

Data Index: 41509 (C4 (Web Text))

Max Activating Token Index: 812

Text #3

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0518. Min Act: -0.0001

Data Index: 657905 (C4 (Web Text))

Max Activating Token Index: 448

Text #4

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0516. Min Act: -0.0001

Data Index: 41356 (C4 (Web Text))

Max Activating Token Index: 261

Text #5

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0511. Min Act: -0.0001

Data Index: 1041738 (C4 (Web Text))

Max Activating Token Index: 703

Text #6

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0523. Min Act: -0.0001

Data Index: 776561 (C4 (Web Text))

Max Activating Token Index: 848

Text #7

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0505. Min Act: -0.0002

Data Index: 1276730 (C4 (Web Text))

Max Activating Token Index: 952

Text #8

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0543. Min Act: -0.0001

Data Index: 770974 (C4 (Web Text))

Max Activating Token Index: 174

Text #9

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0520. Min Act: -0.0001

Data Index: 871607 (C4 (Web Text))

Max Activating Token Index: 166

Text #10

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0518. Min Act: -0.0001

Data Index: 604282 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0508. Min Act: -0.0001

Data Index: 440611 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0508. Min Act: -0.0001

Data Index: 84817 (C4 (Web Text))

Max Activating Token Index: 289

Text #13

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0507. Min Act: -0.0002

Data Index: 940929 (C4 (Web Text))

Max Activating Token Index: 658

Text #14

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0504. Min Act: -0.0002

Data Index: 909154 (C4 (Web Text))

Max Activating Token Index: 1009

Text #15

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1127355 (C4 (Web Text))

Max Activating Token Index: 995

Text #16

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0497. Min Act: -0.0002

Data Index: 180552 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0489. Min Act: -0.0002

Data Index: 262145 (C4 (Web Text))

Max Activating Token Index: 941

Text #18

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0502. Min Act: -0.0001

Data Index: 742675 (C4 (Web Text))

Max Activating Token Index: 877

Text #19

Max Range: 0.0797. Min Range: -0.0797

Max Act: 0.0488. Min Act: -0.0001

Data Index: 404089 (C4 (Web Text))

Max Activating Token Index: 259