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

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

Neuron 472 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.0966. Min Act: -0.0000

Data Index: 12471 (C4 (Web Text))

Max Activating Token Index: 162

Text #1

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.0636. Min Act: -0.0000

Data Index: 717203 (C4 (Web Text))

Max Activating Token Index: 777

Text #2

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.1478. Min Act: -0.0000

Data Index: 1121473 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.0901. Min Act: -0.0000

Data Index: 48055 (C4 (Web Text))

Max Activating Token Index: 594

Text #4

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.1631. Min Act: -0.0000

Data Index: 621443 (C4 (Web Text))

Max Activating Token Index: 212

Text #5

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.0253. Min Act: -0.0000

Data Index: 231910 (C4 (Web Text))

Max Activating Token Index: 378

Text #6

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9945. Min Act: -0.0000

Data Index: 1356390 (C4 (Web Text))

Max Activating Token Index: 235

Text #7

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.0131. Min Act: -0.0000

Data Index: 189751 (C4 (Web Text))

Max Activating Token Index: 453

Text #8

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.0385. Min Act: -0.0000

Data Index: 543791 (C4 (Web Text))

Max Activating Token Index: 343

Text #9

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9429. Min Act: -0.0000

Data Index: 524411 (C4 (Web Text))

Max Activating Token Index: 288

Text #10

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9611. Min Act: -0.0000

Data Index: 1098518 (C4 (Web Text))

Max Activating Token Index: 826

Text #11

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9350. Min Act: -0.0000

Data Index: 238741 (C4 (Web Text))

Max Activating Token Index: 555

Text #12

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9568. Min Act: -0.0000

Data Index: 183074 (C4 (Web Text))

Max Activating Token Index: 600

Text #13

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9039. Min Act: -0.0000

Data Index: 885959 (C4 (Web Text))

Max Activating Token Index: 619

Text #14

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9554. Min Act: -0.0000

Data Index: 1201899 (C4 (Web Text))

Max Activating Token Index: 350

Text #15

Max Range: 1.1631. Min Range: -1.1631

Max Act: 1.0333. Min Act: -0.0000

Data Index: 792292 (C4 (Web Text))

Max Activating Token Index: 239

Text #16

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.8470. Min Act: -0.0000

Data Index: 578456 (C4 (Web Text))

Max Activating Token Index: 219

Text #17

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9698. Min Act: -0.0000

Data Index: 513579 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9415. Min Act: -0.0000

Data Index: 990840 (C4 (Web Text))

Max Activating Token Index: 571

Text #19

Max Range: 1.1631. Min Range: -1.1631

Max Act: 0.9147. Min Act: -0.0000

Data Index: 18878 (C4 (Web Text))

Max Activating Token Index: 899