Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1392 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0760. Min Act: -0.0006

Data Index: 1237851 (C4 (Web Text))

Max Activating Token Index: 271

Text #1

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0702. Min Act: -0.0006

Data Index: 558133 (C4 (Web Text))

Max Activating Token Index: 894

Text #2

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0761. Min Act: -0.0006

Data Index: 589252 (C4 (Web Text))

Max Activating Token Index: 416

Text #3

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0724. Min Act: -0.0006

Data Index: 4111 (C4 (Web Text))

Max Activating Token Index: 780

Text #4

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0626. Min Act: -0.0006

Data Index: 1133740 (C4 (Web Text))

Max Activating Token Index: 260

Text #5

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0670. Min Act: -0.0006

Data Index: 950297 (C4 (Web Text))

Max Activating Token Index: 873

Text #6

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0686. Min Act: -0.0006

Data Index: 116716 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0630. Min Act: -0.0006

Data Index: 279022 (C4 (Web Text))

Max Activating Token Index: 289

Text #8

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0677. Min Act: -0.0006

Data Index: 935631 (C4 (Web Text))

Max Activating Token Index: 552

Text #9

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0620. Min Act: -0.0006

Data Index: 1300673 (C4 (Web Text))

Max Activating Token Index: 278

Text #10

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0642. Min Act: -0.0006

Data Index: 1315803 (C4 (Web Text))

Max Activating Token Index: 327

Text #11

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0631. Min Act: -0.0006

Data Index: 885207 (C4 (Web Text))

Max Activating Token Index: 157

Text #12

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0652. Min Act: -0.0006

Data Index: 1226655 (C4 (Web Text))

Max Activating Token Index: 805

Text #13

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0529. Min Act: -0.0006

Data Index: 267991 (C4 (Web Text))

Max Activating Token Index: 672

Text #14

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0571. Min Act: -0.0006

Data Index: 455624 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0611. Min Act: -0.0006

Data Index: 172517 (C4 (Web Text))

Max Activating Token Index: 607

Text #16

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0591. Min Act: -0.0006

Data Index: 387011 (C4 (Web Text))

Max Activating Token Index: 587

Text #17

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0563. Min Act: -0.0006

Data Index: 1308479 (C4 (Web Text))

Max Activating Token Index: 920

Text #18

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0586. Min Act: -0.0006

Data Index: 178049 (C4 (Web Text))

Max Activating Token Index: 452

Text #19

Max Range: 0.0761. Min Range: -0.0761

Max Act: 0.0613. Min Act: -0.0006

Data Index: 600900 (C4 (Web Text))

Max Activating Token Index: 1012