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

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

Neuron 3294 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1508. Min Range: -2.1508

Max Act: 2.0045. Min Act: -0.0000

Data Index: 805299 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 2.1508. Min Range: -2.1508

Max Act: 2.0279. Min Act: -0.0000

Data Index: 1124474 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.9366. Min Act: -0.0000

Data Index: 1224501 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 2.1508. Min Range: -2.1508

Max Act: 2.1508. Min Act: -0.0000

Data Index: 719858 (C4 (Web Text))

Max Activating Token Index: 408

Text #4

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.9743. Min Act: -0.0000

Data Index: 166388 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8497. Min Act: -0.0000

Data Index: 1128316 (C4 (Web Text))

Max Activating Token Index: 728

Text #6

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7197. Min Act: -0.0000

Data Index: 171622 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7542. Min Act: -0.0000

Data Index: 659046 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8710. Min Act: -0.0000

Data Index: 707882 (C4 (Web Text))

Max Activating Token Index: 503

Text #9

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8689. Min Act: -0.0000

Data Index: 586311 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8551. Min Act: -0.0000

Data Index: 191634 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.6868. Min Act: -0.0000

Data Index: 588839 (C4 (Web Text))

Max Activating Token Index: 810

Text #12

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.6563. Min Act: -0.0000

Data Index: 1268103 (C4 (Web Text))

Max Activating Token Index: 922

Text #13

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8051. Min Act: -0.0000

Data Index: 330583 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8125. Min Act: -0.0000

Data Index: 919779 (C4 (Web Text))

Max Activating Token Index: 808

Text #15

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8078. Min Act: -0.0000

Data Index: 1073677 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.9179. Min Act: -0.0000

Data Index: 353285 (C4 (Web Text))

Max Activating Token Index: 731

Text #17

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8566. Min Act: -0.0000

Data Index: 459594 (C4 (Web Text))

Max Activating Token Index: 552

Text #18

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.7941. Min Act: -0.0000

Data Index: 11689 (C4 (Web Text))

Max Activating Token Index: 699

Text #19

Max Range: 2.1508. Min Range: -2.1508

Max Act: 1.8416. Min Act: -0.0000

Data Index: 423261 (C4 (Web Text))

Max Activating Token Index: 691