Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 5397 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2541. Min Act: -0.0001

Data Index: 1156205 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2283. Min Act: -0.0001

Data Index: 928167 (C4 (Web Text))

Max Activating Token Index: 157

Text #2

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2147. Min Act: -0.0001

Data Index: 1061635 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2015. Min Act: -0.0001

Data Index: 1213186 (C4 (Web Text))

Max Activating Token Index: 948

Text #4

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1994. Min Act: -0.0001

Data Index: 290801 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1979. Min Act: -0.0001

Data Index: 624637 (C4 (Web Text))

Max Activating Token Index: 857

Text #6

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2091. Min Act: -0.0001

Data Index: 546519 (C4 (Web Text))

Max Activating Token Index: 382

Text #7

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1969. Min Act: -0.0001

Data Index: 464779 (C4 (Web Text))

Max Activating Token Index: 170

Text #8

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1880. Min Act: -0.0001

Data Index: 774317 (C4 (Web Text))

Max Activating Token Index: 606

Text #9

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2000. Min Act: -0.0001

Data Index: 576035 (C4 (Web Text))

Max Activating Token Index: 155

Text #10

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.2014. Min Act: -0.0001

Data Index: 145285 (C4 (Web Text))

Max Activating Token Index: 670

Text #11

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1819. Min Act: -0.0001

Data Index: 393157 (C4 (Web Text))

Max Activating Token Index: 644

Text #12

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1649. Min Act: -0.0001

Data Index: 436907 (C4 (Web Text))

Max Activating Token Index: 722

Text #13

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1748. Min Act: -0.0001

Data Index: 780411 (C4 (Web Text))

Max Activating Token Index: 484

Text #14

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1783. Min Act: -0.0001

Data Index: 311934 (C4 (Web Text))

Max Activating Token Index: 936

Text #15

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1863. Min Act: -0.0001

Data Index: 497186 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1833. Min Act: -0.0001

Data Index: 1289230 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1605. Min Act: -0.0001

Data Index: 476964 (C4 (Web Text))

Max Activating Token Index: 828

Text #18

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1799. Min Act: -0.0001

Data Index: 389506 (C4 (Web Text))

Max Activating Token Index: 81

Text #19

Max Range: 0.2541. Min Range: -0.2541

Max Act: 0.1683. Min Act: -0.0001

Data Index: 1333772 (C4 (Web Text))

Max Activating Token Index: 13