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

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

Neuron 4707 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.9317. Min Act: -0.0000

Data Index: 627236 (C4 (Web Text))

Max Activating Token Index: 711

Text #1

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7815. Min Act: -0.0000

Data Index: 1284302 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7807. Min Act: -0.0000

Data Index: 536712 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7483. Min Act: -0.0000

Data Index: 1145080 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7417. Min Act: -0.0000

Data Index: 850905 (C4 (Web Text))

Max Activating Token Index: 651

Text #5

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7510. Min Act: -0.0000

Data Index: 559439 (C4 (Web Text))

Max Activating Token Index: 804

Text #6

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7541. Min Act: -0.0000

Data Index: 1117455 (C4 (Web Text))

Max Activating Token Index: 802

Text #7

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7346. Min Act: -0.0000

Data Index: 930922 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7446. Min Act: -0.0000

Data Index: 55628 (C4 (Web Text))

Max Activating Token Index: 895

Text #9

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.6628. Min Act: -0.0000

Data Index: 1263522 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7039. Min Act: -0.0000

Data Index: 1351242 (C4 (Web Text))

Max Activating Token Index: 363

Text #11

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7292. Min Act: -0.0000

Data Index: 1222392 (C4 (Web Text))

Max Activating Token Index: 777

Text #12

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1052066 (C4 (Web Text))

Max Activating Token Index: 3

Text #13

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.5578. Min Act: -0.0000

Data Index: 1226458 (C4 (Web Text))

Max Activating Token Index: 3

Text #14

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.6556. Min Act: -0.0000

Data Index: 760214 (C4 (Web Text))

Max Activating Token Index: 113

Text #15

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.6969. Min Act: -0.0000

Data Index: 201125 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.7176. Min Act: -0.0000

Data Index: 800803 (C4 (Web Text))

Max Activating Token Index: 886

Text #17

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.6740. Min Act: -0.0001

Data Index: 830116 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.6635. Min Act: -0.0000

Data Index: 474011 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.9317. Min Range: -0.9317

Max Act: 0.6795. Min Act: -0.0001

Data Index: 819373 (C4 (Web Text))

Max Activating Token Index: 707