Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4544 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.8604. Min Act: -0.0001

Data Index: 505379 (C4 (Web Text))

Max Activating Token Index: 229

Text #1

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6684. Min Act: -0.0001

Data Index: 288161 (C4 (Web Text))

Max Activating Token Index: 123

Text #2

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.7582. Min Act: -0.0001

Data Index: 891578 (C4 (Web Text))

Max Activating Token Index: 319

Text #3

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6223. Min Act: -0.0001

Data Index: 485409 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6054. Min Act: -0.0001

Data Index: 567665 (C4 (Web Text))

Max Activating Token Index: 598

Text #5

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5777. Min Act: -0.0001

Data Index: 151153 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6406. Min Act: -0.0001

Data Index: 304067 (C4 (Web Text))

Max Activating Token Index: 156

Text #7

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5956. Min Act: -0.0001

Data Index: 978935 (C4 (Web Text))

Max Activating Token Index: 163

Text #8

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5352. Min Act: -0.0001

Data Index: 778269 (C4 (Web Text))

Max Activating Token Index: 590

Text #9

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5533. Min Act: -0.0001

Data Index: 609890 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.6479. Min Act: -0.0001

Data Index: 988917 (C4 (Web Text))

Max Activating Token Index: 642

Text #11

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5757. Min Act: -0.0001

Data Index: 536654 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5613. Min Act: -0.0001

Data Index: 59428 (C4 (Web Text))

Max Activating Token Index: 969

Text #13

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5710. Min Act: -0.0001

Data Index: 229348 (C4 (Web Text))

Max Activating Token Index: 82

Text #14

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5736. Min Act: -0.0001

Data Index: 856886 (C4 (Web Text))

Max Activating Token Index: 436

Text #15

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5091. Min Act: -0.0001

Data Index: 1036274 (C4 (Web Text))

Max Activating Token Index: 832

Text #16

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5985. Min Act: -0.0001

Data Index: 1202170 (C4 (Web Text))

Max Activating Token Index: 547

Text #17

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5015. Min Act: -0.0001

Data Index: 1128149 (C4 (Web Text))

Max Activating Token Index: 877

Text #18

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.5345. Min Act: -0.0001

Data Index: 558318 (C4 (Web Text))

Max Activating Token Index: 143

Text #19

Max Range: 0.8604. Min Range: -0.8604

Max Act: 0.4990. Min Act: -0.0001

Data Index: 515326 (C4 (Web Text))

Max Activating Token Index: 465