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

Dataset: The Pile

Neuron 1208 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3492. Min Act: -0.0000

Data Index: 327237 (The Pile)

Max Activating Token Index: 865

Text #1

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.3541. Min Act: -0.0000

Data Index: 1787588 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2927. Min Act: -0.0000

Data Index: 335126 (The Pile)

Max Activating Token Index: 693

Text #3

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2888. Min Act: -0.0000

Data Index: 1496419 (The Pile)

Max Activating Token Index: 358

Text #4

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2993. Min Act: -0.0000

Data Index: 1368506 (The Pile)

Max Activating Token Index: 861

Text #5

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2974. Min Act: -0.0000

Data Index: 1245313 (The Pile)

Max Activating Token Index: 686

Text #6

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2616. Min Act: -0.0000

Data Index: 1342838 (The Pile)

Max Activating Token Index: 692

Text #7

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2540. Min Act: -0.0000

Data Index: 1722262 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2515. Min Act: -0.0000

Data Index: 1811817 (The Pile)

Max Activating Token Index: 976

Text #9

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2765. Min Act: -0.0000

Data Index: 1534920 (The Pile)

Max Activating Token Index: 688

Text #10

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2755. Min Act: -0.0000

Data Index: 335017 (The Pile)

Max Activating Token Index: 64

Text #11

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2691. Min Act: -0.0000

Data Index: 156507 (The Pile)

Max Activating Token Index: 470

Text #12

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2758. Min Act: -0.0000

Data Index: 768159 (The Pile)

Max Activating Token Index: 670

Text #13

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2581. Min Act: -0.0000

Data Index: 164513 (The Pile)

Max Activating Token Index: 304

Text #14

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2583. Min Act: -0.0000

Data Index: 43528 (The Pile)

Max Activating Token Index: 451

Text #15

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2415. Min Act: -0.0000

Data Index: 881161 (The Pile)

Max Activating Token Index: 845

Text #16

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2591. Min Act: -0.0000

Data Index: 80118 (The Pile)

Max Activating Token Index: 436

Text #17

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2391. Min Act: -0.0000

Data Index: 1089761 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2547. Min Act: -0.0000

Data Index: 1141370 (The Pile)

Max Activating Token Index: 56

Text #19

Max Range: 0.3541. Min Range: -0.3541

Max Act: 0.2273. Min Act: -0.0001

Data Index: 1028999 (The Pile)

Max Activating Token Index: 647