Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 475 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0750. Min Act: -0.0001

Data Index: 238431 (C4 (Web Text))

Max Activating Token Index: 184

Text #1

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0626. Min Act: -0.0001

Data Index: 623310 (C4 (Web Text))

Max Activating Token Index: 787

Text #2

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0594. Min Act: -0.0001

Data Index: 926914 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0572. Min Act: -0.0001

Data Index: 221067 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0589. Min Act: -0.0001

Data Index: 203212 (C4 (Web Text))

Max Activating Token Index: 134

Text #5

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0590. Min Act: -0.0001

Data Index: 685822 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0585. Min Act: -0.0001

Data Index: 223695 (C4 (Web Text))

Max Activating Token Index: 822

Text #7

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0594. Min Act: -0.0001

Data Index: 734697 (C4 (Web Text))

Max Activating Token Index: 761

Text #8

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0523. Min Act: -0.0001

Data Index: 1143329 (C4 (Web Text))

Max Activating Token Index: 956

Text #9

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0538. Min Act: -0.0001

Data Index: 1277512 (C4 (Web Text))

Max Activating Token Index: 424

Text #10

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0554. Min Act: -0.0001

Data Index: 36794 (C4 (Web Text))

Max Activating Token Index: 761

Text #11

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0527. Min Act: -0.0001

Data Index: 21391 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0616. Min Act: -0.0001

Data Index: 519259 (C4 (Web Text))

Max Activating Token Index: 899

Text #13

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0546. Min Act: -0.0001

Data Index: 900065 (C4 (Web Text))

Max Activating Token Index: 880

Text #14

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0540. Min Act: -0.0001

Data Index: 313012 (C4 (Web Text))

Max Activating Token Index: 123

Text #15

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0499. Min Act: -0.0001

Data Index: 325099 (C4 (Web Text))

Max Activating Token Index: 579

Text #16

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0538. Min Act: -0.0001

Data Index: 738855 (C4 (Web Text))

Max Activating Token Index: 783

Text #17

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0557. Min Act: -0.0001

Data Index: 356548 (C4 (Web Text))

Max Activating Token Index: 672

Text #18

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0550. Min Act: -0.0001

Data Index: 791365 (C4 (Web Text))

Max Activating Token Index: 309

Text #19

Max Range: 0.0750. Min Range: -0.0750

Max Act: 0.0509. Min Act: -0.0001

Data Index: 91376 (C4 (Web Text))

Max Activating Token Index: 834