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

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

Neuron 3568 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: 1.0502. Min Range: -1.0502

Max Act: 1.0502. Min Act: -0.0001

Data Index: 134668 (C4 (Web Text))

Max Activating Token Index: 525

Text #1

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9693. Min Act: -0.0001

Data Index: 639293 (C4 (Web Text))

Max Activating Token Index: 548

Text #2

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9481. Min Act: -0.0001

Data Index: 32651 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9719. Min Act: -0.0001

Data Index: 872107 (C4 (Web Text))

Max Activating Token Index: 674

Text #4

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9852. Min Act: -0.0001

Data Index: 919051 (C4 (Web Text))

Max Activating Token Index: 699

Text #5

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9845. Min Act: -0.0001

Data Index: 109623 (C4 (Web Text))

Max Activating Token Index: 524

Text #6

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8508. Min Act: -0.0001

Data Index: 496670 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8905. Min Act: -0.0001

Data Index: 254430 (C4 (Web Text))

Max Activating Token Index: 918

Text #8

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9080. Min Act: -0.0001

Data Index: 1151374 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8353. Min Act: -0.0001

Data Index: 1140838 (C4 (Web Text))

Max Activating Token Index: 881

Text #10

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.9088. Min Act: -0.0001

Data Index: 264959 (C4 (Web Text))

Max Activating Token Index: 602

Text #11

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8386. Min Act: -0.0001

Data Index: 144241 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8272. Min Act: -0.0001

Data Index: 662672 (C4 (Web Text))

Max Activating Token Index: 568

Text #13

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8244. Min Act: -0.0001

Data Index: 733555 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.7642. Min Act: -0.0001

Data Index: 1094114 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.8094. Min Act: -0.0001

Data Index: 1101156 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.7613. Min Act: -0.0001

Data Index: 414181 (C4 (Web Text))

Max Activating Token Index: 206

Text #17

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.7333. Min Act: -0.0001

Data Index: 189732 (C4 (Web Text))

Max Activating Token Index: 286

Text #18

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.7375. Min Act: -0.0001

Data Index: 51759 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 1.0502. Min Range: -1.0502

Max Act: 0.7446. Min Act: -0.0001

Data Index: 555794 (C4 (Web Text))

Max Activating Token Index: 868