Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3963 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.9600. Min Act: -0.0000

Data Index: 1411574 (Python Code)

Max Activating Token Index: 612

Text #1

Max Range: 2.0068. Min Range: -2.0068

Max Act: 2.0068. Min Act: -0.0000

Data Index: 1526122 (Python Code)

Max Activating Token Index: 913

Text #2

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.8823. Min Act: -0.0000

Data Index: 1416855 (Python Code)

Max Activating Token Index: 878

Text #3

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.8071. Min Act: -0.0000

Data Index: 1634813 (Python Code)

Max Activating Token Index: 697

Text #4

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.6737. Min Act: -0.0000

Data Index: 1492784 (Python Code)

Max Activating Token Index: 790

Text #5

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.6384. Min Act: -0.0000

Data Index: 1626703 (Python Code)

Max Activating Token Index: 463

Text #6

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.5315. Min Act: -0.0000

Data Index: 1636004 (Python Code)

Max Activating Token Index: 219

Text #7

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.5766. Min Act: -0.0000

Data Index: 1533740 (Python Code)

Max Activating Token Index: 140

Text #8

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.4796. Min Act: -0.0000

Data Index: 1437529 (Python Code)

Max Activating Token Index: 192

Text #9

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3326. Min Act: -0.0000

Data Index: 1374884 (Python Code)

Max Activating Token Index: 237

Text #10

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3367. Min Act: -0.0000

Data Index: 1450134 (Python Code)

Max Activating Token Index: 126

Text #11

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3688. Min Act: -0.0000

Data Index: 1582432 (Python Code)

Max Activating Token Index: 560

Text #12

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3683. Min Act: -0.0000

Data Index: 1547794 (Python Code)

Max Activating Token Index: 633

Text #13

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3566. Min Act: -0.0000

Data Index: 1510706 (Python Code)

Max Activating Token Index: 866

Text #14

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3528. Min Act: -0.0000

Data Index: 1594050 (Python Code)

Max Activating Token Index: 633

Text #15

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3436. Min Act: -0.0000

Data Index: 1632355 (Python Code)

Max Activating Token Index: 794

Text #16

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3336. Min Act: -0.0000

Data Index: 1645370 (Python Code)

Max Activating Token Index: 336

Text #17

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3352. Min Act: -0.0000

Data Index: 1027184 (C4 (Web Text))

Max Activating Token Index: 605

Text #18

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.2631. Min Act: -0.0000

Data Index: 1384650 (Python Code)

Max Activating Token Index: 965

Text #19

Max Range: 2.0068. Min Range: -2.0068

Max Act: 1.3382. Min Act: -0.0000

Data Index: 1639450 (Python Code)

Max Activating Token Index: 829