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

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

Neuron 386 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.9064. Min Act: -0.0001

Data Index: 317574 (C4 (Web Text))

Max Activating Token Index: 7

Text #1

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8421. Min Act: -0.0001

Data Index: 630308 (C4 (Web Text))

Max Activating Token Index: 936

Text #2

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.8687. Min Act: -0.0001

Data Index: 1250155 (C4 (Web Text))

Max Activating Token Index: 484

Text #3

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7868. Min Act: -0.0001

Data Index: 110331 (C4 (Web Text))

Max Activating Token Index: 896

Text #4

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7872. Min Act: -0.0001

Data Index: 185648 (C4 (Web Text))

Max Activating Token Index: 500

Text #5

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7219. Min Act: -0.0001

Data Index: 110800 (C4 (Web Text))

Max Activating Token Index: 932

Text #6

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6866. Min Act: -0.0001

Data Index: 835512 (C4 (Web Text))

Max Activating Token Index: 557

Text #7

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7738. Min Act: -0.0001

Data Index: 293941 (C4 (Web Text))

Max Activating Token Index: 477

Text #8

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7265. Min Act: -0.0001

Data Index: 390557 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.7222. Min Act: -0.0001

Data Index: 978654 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6591. Min Act: -0.0001

Data Index: 93399 (C4 (Web Text))

Max Activating Token Index: 183

Text #11

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6940. Min Act: -0.0001

Data Index: 940841 (C4 (Web Text))

Max Activating Token Index: 303

Text #12

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6935. Min Act: -0.0001

Data Index: 582680 (C4 (Web Text))

Max Activating Token Index: 584

Text #13

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6417. Min Act: -0.0001

Data Index: 760012 (C4 (Web Text))

Max Activating Token Index: 693

Text #14

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6588. Min Act: -0.0001

Data Index: 571329 (C4 (Web Text))

Max Activating Token Index: 442

Text #15

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6277. Min Act: -0.0001

Data Index: 168642 (C4 (Web Text))

Max Activating Token Index: 136

Text #16

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6428. Min Act: -0.0001

Data Index: 678410 (C4 (Web Text))

Max Activating Token Index: 190

Text #17

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6770. Min Act: -0.0001

Data Index: 273873 (C4 (Web Text))

Max Activating Token Index: 652

Text #18

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.5875. Min Act: -0.0001

Data Index: 749472 (C4 (Web Text))

Max Activating Token Index: 767

Text #19

Max Range: 0.9064. Min Range: -0.9064

Max Act: 0.6163. Min Act: -0.0001

Data Index: 535923 (C4 (Web Text))

Max Activating Token Index: 413