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

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

Neuron 2379 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.0918. Min Range: -1.0918

Max Act: 1.0918. Min Act: -0.0000

Data Index: 133380 (C4 (Web Text))

Max Activating Token Index: 141

Text #1

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9807. Min Act: -0.0000

Data Index: 1103985 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.9598. Min Act: -0.0001

Data Index: 826598 (C4 (Web Text))

Max Activating Token Index: 28

Text #3

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.8772. Min Act: -0.0000

Data Index: 46844 (C4 (Web Text))

Max Activating Token Index: 111

Text #4

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7465. Min Act: -0.0001

Data Index: 1613761 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7246. Min Act: -0.0000

Data Index: 420503 (C4 (Web Text))

Max Activating Token Index: 45

Text #6

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6845. Min Act: -0.0001

Data Index: 630761 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7092. Min Act: -0.0001

Data Index: 1198125 (C4 (Web Text))

Max Activating Token Index: 762

Text #8

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6980. Min Act: -0.0001

Data Index: 1594020 (Python Code)

Max Activating Token Index: 1012

Text #9

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6859. Min Act: -0.0001

Data Index: 1517228 (Python Code)

Max Activating Token Index: 468

Text #10

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6605. Min Act: -0.0000

Data Index: 1340654 (C4 (Web Text))

Max Activating Token Index: 592

Text #11

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6536. Min Act: -0.0001

Data Index: 1475001 (Python Code)

Max Activating Token Index: 995

Text #12

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.7159. Min Act: -0.0001

Data Index: 1513406 (Python Code)

Max Activating Token Index: 985

Text #13

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6744. Min Act: -0.0001

Data Index: 1502995 (Python Code)

Max Activating Token Index: 526

Text #14

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6666. Min Act: -0.0001

Data Index: 1506462 (Python Code)

Max Activating Token Index: 643

Text #15

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6499. Min Act: -0.0001

Data Index: 1524510 (Python Code)

Max Activating Token Index: 622

Text #16

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6493. Min Act: -0.0000

Data Index: 275647 (C4 (Web Text))

Max Activating Token Index: 247

Text #17

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6665. Min Act: -0.0001

Data Index: 1445957 (Python Code)

Max Activating Token Index: 160

Text #18

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6623. Min Act: -0.0001

Data Index: 1462573 (Python Code)

Max Activating Token Index: 764

Text #19

Max Range: 1.0918. Min Range: -1.0918

Max Act: 0.6532. Min Act: -0.0001

Data Index: 1557590 (Python Code)

Max Activating Token Index: 956