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

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

Neuron 2741 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.7787. Min Act: 0.0000

Data Index: 1507811 (Python Code)

Max Activating Token Index: 39

Text #1

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6780. Min Act: 0.0000

Data Index: 1625515 (Python Code)

Max Activating Token Index: 457

Text #2

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6304. Min Act: 0.0001

Data Index: 1559952 (Python Code)

Max Activating Token Index: 731

Text #3

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5997. Min Act: 0.0001

Data Index: 1645376 (Python Code)

Max Activating Token Index: 215

Text #4

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6047. Min Act: 0.0000

Data Index: 1445378 (Python Code)

Max Activating Token Index: 50

Text #5

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6122. Min Act: -0.0000

Data Index: 1537372 (Python Code)

Max Activating Token Index: 162

Text #6

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5951. Min Act: 0.0000

Data Index: 1418224 (Python Code)

Max Activating Token Index: 602

Text #7

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5560. Min Act: 0.0000

Data Index: 1450967 (Python Code)

Max Activating Token Index: 492

Text #8

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5624. Min Act: -0.0000

Data Index: 1576588 (Python Code)

Max Activating Token Index: 955

Text #9

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.6076. Min Act: -0.0000

Data Index: 1511444 (Python Code)

Max Activating Token Index: 62

Text #10

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1385795 (Python Code)

Max Activating Token Index: 947

Text #11

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5651. Min Act: 0.0001

Data Index: 1388478 (Python Code)

Max Activating Token Index: 914

Text #12

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1587592 (Python Code)

Max Activating Token Index: 138

Text #13

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5709. Min Act: 0.0000

Data Index: 1487414 (Python Code)

Max Activating Token Index: 549

Text #14

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5542. Min Act: 0.0000

Data Index: 1517518 (Python Code)

Max Activating Token Index: 591

Text #15

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5366. Min Act: 0.0000

Data Index: 1482803 (Python Code)

Max Activating Token Index: 459

Text #16

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.4733. Min Act: 0.0001

Data Index: 1598650 (Python Code)

Max Activating Token Index: 152

Text #17

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.4785. Min Act: -0.0000

Data Index: 1462747 (Python Code)

Max Activating Token Index: 394

Text #18

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.5353. Min Act: -0.0000

Data Index: 1412974 (Python Code)

Max Activating Token Index: 163

Text #19

Max Range: 0.7787. Min Range: -0.7787

Max Act: 0.4827. Min Act: 0.0000

Data Index: 1606619 (Python Code)

Max Activating Token Index: 869