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

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

Neuron 4012 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: 0.1751. Min Range: -0.1751

Max Act: 0.1751. Min Act: -0.0000

Data Index: 323613 (C4 (Web Text))

Max Activating Token Index: 1014

Text #1

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1564. Min Act: -0.0001

Data Index: 784665 (C4 (Web Text))

Max Activating Token Index: 610

Text #2

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1506. Min Act: -0.0001

Data Index: 877947 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1506. Min Act: -0.0001

Data Index: 761231 (C4 (Web Text))

Max Activating Token Index: 317

Text #4

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1604. Min Act: -0.0001

Data Index: 722629 (C4 (Web Text))

Max Activating Token Index: 267

Text #5

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1684. Min Act: -0.0000

Data Index: 414878 (C4 (Web Text))

Max Activating Token Index: 972

Text #6

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1544. Min Act: -0.0001

Data Index: 889116 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1614. Min Act: -0.0001

Data Index: 114677 (C4 (Web Text))

Max Activating Token Index: 520

Text #8

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1486. Min Act: -0.0001

Data Index: 1004209 (C4 (Web Text))

Max Activating Token Index: 219

Text #9

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1495. Min Act: -0.0000

Data Index: 579347 (C4 (Web Text))

Max Activating Token Index: 609

Text #10

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1526. Min Act: -0.0000

Data Index: 925975 (C4 (Web Text))

Max Activating Token Index: 895

Text #11

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1474. Min Act: -0.0001

Data Index: 1110647 (C4 (Web Text))

Max Activating Token Index: 926

Text #12

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1459. Min Act: -0.0000

Data Index: 886680 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1438. Min Act: -0.0001

Data Index: 542045 (C4 (Web Text))

Max Activating Token Index: 212

Text #14

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1426. Min Act: -0.0000

Data Index: 28033 (C4 (Web Text))

Max Activating Token Index: 69

Text #15

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1302. Min Act: -0.0001

Data Index: 1278467 (C4 (Web Text))

Max Activating Token Index: 901

Text #16

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1397. Min Act: -0.0000

Data Index: 885877 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1444. Min Act: -0.0000

Data Index: 692911 (C4 (Web Text))

Max Activating Token Index: 189

Text #18

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1486. Min Act: -0.0000

Data Index: 229255 (C4 (Web Text))

Max Activating Token Index: 938

Text #19

Max Range: 0.1751. Min Range: -0.1751

Max Act: 0.1380. Min Act: -0.0000

Data Index: 1107768 (C4 (Web Text))

Max Activating Token Index: 563