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

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

Neuron 501 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.7685. Min Act: -0.0001

Data Index: 1326329 (C4 (Web Text))

Max Activating Token Index: 226

Text #1

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.7708. Min Act: -0.0001

Data Index: 796587 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.7194. Min Act: -0.0001

Data Index: 262216 (C4 (Web Text))

Max Activating Token Index: 133

Text #3

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.7236. Min Act: -0.0001

Data Index: 611156 (C4 (Web Text))

Max Activating Token Index: 621

Text #4

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.7479. Min Act: -0.0001

Data Index: 340523 (C4 (Web Text))

Max Activating Token Index: 147

Text #5

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6683. Min Act: -0.0001

Data Index: 360239 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6487. Min Act: -0.0001

Data Index: 372881 (C4 (Web Text))

Max Activating Token Index: 740

Text #7

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6917. Min Act: -0.0001

Data Index: 670571 (C4 (Web Text))

Max Activating Token Index: 776

Text #8

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6701. Min Act: -0.0001

Data Index: 663012 (C4 (Web Text))

Max Activating Token Index: 116

Text #9

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6372. Min Act: -0.0001

Data Index: 624565 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6795. Min Act: -0.0001

Data Index: 67487 (C4 (Web Text))

Max Activating Token Index: 506

Text #11

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6324. Min Act: -0.0001

Data Index: 984418 (C4 (Web Text))

Max Activating Token Index: 435

Text #12

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6391. Min Act: -0.0001

Data Index: 776226 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6224. Min Act: -0.0001

Data Index: 561377 (C4 (Web Text))

Max Activating Token Index: 634

Text #14

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6752. Min Act: -0.0001

Data Index: 628155 (C4 (Web Text))

Max Activating Token Index: 737

Text #15

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.5520. Min Act: -0.0001

Data Index: 135633 (C4 (Web Text))

Max Activating Token Index: 526

Text #16

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6831. Min Act: -0.0001

Data Index: 1326047 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6896. Min Act: -0.0001

Data Index: 1236622 (C4 (Web Text))

Max Activating Token Index: 880

Text #18

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.6589. Min Act: -0.0001

Data Index: 993913 (C4 (Web Text))

Max Activating Token Index: 592

Text #19

Max Range: 0.7708. Min Range: -0.7708

Max Act: 0.5703. Min Act: -0.0001

Data Index: 135225 (C4 (Web Text))

Max Activating Token Index: 945