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

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

Neuron 605 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: 1.1015. Min Range: -1.1015

Max Act: 1.1015. Min Act: -0.0001

Data Index: 573389 (C4 (Web Text))

Max Activating Token Index: 242

Text #1

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9903. Min Act: -0.0001

Data Index: 859863 (C4 (Web Text))

Max Activating Token Index: 257

Text #2

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9089. Min Act: -0.0001

Data Index: 925794 (C4 (Web Text))

Max Activating Token Index: 986

Text #3

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8817. Min Act: -0.0001

Data Index: 1134692 (C4 (Web Text))

Max Activating Token Index: 1016

Text #4

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.9105. Min Act: -0.0001

Data Index: 126708 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8329. Min Act: -0.0001

Data Index: 981867 (C4 (Web Text))

Max Activating Token Index: 374

Text #6

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8679. Min Act: -0.0001

Data Index: 1232907 (C4 (Web Text))

Max Activating Token Index: 158

Text #7

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8451. Min Act: -0.0001

Data Index: 335142 (C4 (Web Text))

Max Activating Token Index: 344

Text #8

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8430. Min Act: -0.0001

Data Index: 1261513 (C4 (Web Text))

Max Activating Token Index: 640

Text #9

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8014. Min Act: -0.0001

Data Index: 1040207 (C4 (Web Text))

Max Activating Token Index: 153

Text #10

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8598. Min Act: -0.0001

Data Index: 1327325 (C4 (Web Text))

Max Activating Token Index: 877

Text #11

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8553. Min Act: -0.0001

Data Index: 125157 (C4 (Web Text))

Max Activating Token Index: 331

Text #12

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8263. Min Act: -0.0001

Data Index: 599110 (C4 (Web Text))

Max Activating Token Index: 693

Text #13

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8277. Min Act: -0.0001

Data Index: 679611 (C4 (Web Text))

Max Activating Token Index: 521

Text #14

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8434. Min Act: -0.0001

Data Index: 856462 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.8207. Min Act: -0.0001

Data Index: 985214 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7702. Min Act: -0.0001

Data Index: 670948 (C4 (Web Text))

Max Activating Token Index: 686

Text #17

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7901. Min Act: -0.0001

Data Index: 674898 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7581. Min Act: -0.0001

Data Index: 1273929 (C4 (Web Text))

Max Activating Token Index: 305

Text #19

Max Range: 1.1015. Min Range: -1.1015

Max Act: 0.7478. Min Act: -0.0001

Data Index: 961715 (C4 (Web Text))

Max Activating Token Index: 673