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

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

Neuron 3940 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.8227. Min Act: -0.0000

Data Index: 906906 (C4 (Web Text))

Max Activating Token Index: 376

Text #1

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.8344. Min Act: -0.0000

Data Index: 234526 (C4 (Web Text))

Max Activating Token Index: 24

Text #2

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7733. Min Act: -0.0001

Data Index: 958520 (C4 (Web Text))

Max Activating Token Index: 608

Text #3

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7312. Min Act: -0.0001

Data Index: 1035041 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7675. Min Act: -0.0000

Data Index: 681517 (C4 (Web Text))

Max Activating Token Index: 864

Text #5

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7210. Min Act: -0.0000

Data Index: 128049 (C4 (Web Text))

Max Activating Token Index: 511

Text #6

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6924. Min Act: -0.0001

Data Index: 1186674 (C4 (Web Text))

Max Activating Token Index: 461

Text #7

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6654. Min Act: -0.0000

Data Index: 794843 (C4 (Web Text))

Max Activating Token Index: 458

Text #8

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6372. Min Act: -0.0000

Data Index: 1263334 (C4 (Web Text))

Max Activating Token Index: 671

Text #9

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6499. Min Act: -0.0000

Data Index: 1244948 (C4 (Web Text))

Max Activating Token Index: 77

Text #10

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6607. Min Act: -0.0001

Data Index: 1126087 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6516. Min Act: -0.0001

Data Index: 368131 (C4 (Web Text))

Max Activating Token Index: 60

Text #12

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.7409. Min Act: -0.0000

Data Index: 869987 (C4 (Web Text))

Max Activating Token Index: 659

Text #13

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6103. Min Act: -0.0000

Data Index: 110312 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6989. Min Act: -0.0001

Data Index: 578180 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6438. Min Act: -0.0000

Data Index: 543426 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6575. Min Act: -0.0001

Data Index: 1311605 (C4 (Web Text))

Max Activating Token Index: 259

Text #17

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6329. Min Act: -0.0001

Data Index: 1123842 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6523. Min Act: -0.0001

Data Index: 1008227 (C4 (Web Text))

Max Activating Token Index: 173

Text #19

Max Range: 0.8344. Min Range: -0.8344

Max Act: 0.6511. Min Act: -0.0000

Data Index: 830891 (C4 (Web Text))

Max Activating Token Index: 305