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

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

Neuron 1830 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0751. Min Act: -0.0001

Data Index: 886094 (C4 (Web Text))

Max Activating Token Index: 675

Text #1

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1024139 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0580. Min Act: -0.0001

Data Index: 553351 (C4 (Web Text))

Max Activating Token Index: 814

Text #3

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0532. Min Act: -0.0000

Data Index: 1056747 (C4 (Web Text))

Max Activating Token Index: 308

Text #4

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0543. Min Act: -0.0001

Data Index: 309946 (C4 (Web Text))

Max Activating Token Index: 614

Text #5

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0519. Min Act: -0.0001

Data Index: 991653 (C4 (Web Text))

Max Activating Token Index: 825

Text #6

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0525. Min Act: -0.0001

Data Index: 1190529 (C4 (Web Text))

Max Activating Token Index: 861

Text #7

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0522. Min Act: -0.0001

Data Index: 1205936 (C4 (Web Text))

Max Activating Token Index: 302

Text #8

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0541. Min Act: -0.0001

Data Index: 545466 (C4 (Web Text))

Max Activating Token Index: 555

Text #9

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0520. Min Act: -0.0001

Data Index: 798191 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0538. Min Act: -0.0000

Data Index: 258959 (C4 (Web Text))

Max Activating Token Index: 317

Text #11

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0517. Min Act: -0.0000

Data Index: 759406 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0501. Min Act: -0.0000

Data Index: 251105 (C4 (Web Text))

Max Activating Token Index: 195

Text #13

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0528. Min Act: -0.0001

Data Index: 804130 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0461. Min Act: -0.0001

Data Index: 235988 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0507. Min Act: -0.0001

Data Index: 582012 (C4 (Web Text))

Max Activating Token Index: 131

Text #16

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0476. Min Act: -0.0000

Data Index: 608701 (C4 (Web Text))

Max Activating Token Index: 546

Text #17

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0433. Min Act: -0.0001

Data Index: 12681 (C4 (Web Text))

Max Activating Token Index: 905

Text #18

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0463. Min Act: -0.0000

Data Index: 1077513 (C4 (Web Text))

Max Activating Token Index: 627

Text #19

Max Range: 0.0751. Min Range: -0.0751

Max Act: 0.0452. Min Act: -0.0001

Data Index: 657227 (C4 (Web Text))

Max Activating Token Index: 1007