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

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

Neuron 2908 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: 1.6573. Min Range: -1.6573

Max Act: 1.6573. Min Act: -0.0000

Data Index: 179705 (C4 (Web Text))

Max Activating Token Index: 836

Text #1

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.5410. Min Act: -0.0000

Data Index: 143113 (C4 (Web Text))

Max Activating Token Index: 602

Text #2

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.4222. Min Act: -0.0000

Data Index: 1344999 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.2690. Min Act: -0.0000

Data Index: 594867 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.2298. Min Act: -0.0000

Data Index: 828151 (C4 (Web Text))

Max Activating Token Index: 944

Text #5

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.2701. Min Act: -0.0000

Data Index: 674510 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.3014. Min Act: -0.0000

Data Index: 827655 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.0989. Min Act: -0.0000

Data Index: 732068 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.0685. Min Act: 0.0000

Data Index: 771542 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 1.6573. Min Range: -1.6573

Max Act: 0.8484. Min Act: -0.0000

Data Index: 627031 (C4 (Web Text))

Max Activating Token Index: 138

Text #10

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.0849. Min Act: -0.0000

Data Index: 150853 (C4 (Web Text))

Max Activating Token Index: 389

Text #11

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.0470. Min Act: -0.0000

Data Index: 895018 (C4 (Web Text))

Max Activating Token Index: 298

Text #12

Max Range: 1.6573. Min Range: -1.6573

Max Act: 0.9936. Min Act: -0.0000

Data Index: 474 (C4 (Web Text))

Max Activating Token Index: 786

Text #13

Max Range: 1.6573. Min Range: -1.6573

Max Act: 1.1200. Min Act: -0.0000

Data Index: 888678 (C4 (Web Text))

Max Activating Token Index: 772

Text #14

Max Range: 1.6573. Min Range: -1.6573

Max Act: 0.8350. Min Act: -0.0000

Data Index: 929928 (C4 (Web Text))

Max Activating Token Index: 875

Text #15

Max Range: 1.6573. Min Range: -1.6573

Max Act: 0.9187. Min Act: -0.0000

Data Index: 602680 (C4 (Web Text))

Max Activating Token Index: 565

Text #16

Max Range: 1.6573. Min Range: -1.6573

Max Act: 0.8691. Min Act: -0.0000

Data Index: 485134 (C4 (Web Text))

Max Activating Token Index: 582

Text #17

Max Range: 1.6573. Min Range: -1.6573

Max Act: 0.9347. Min Act: -0.0000

Data Index: 327527 (C4 (Web Text))

Max Activating Token Index: 340

Text #18

Max Range: 1.6573. Min Range: -1.6573

Max Act: 0.8622. Min Act: -0.0000

Data Index: 613857 (C4 (Web Text))

Max Activating Token Index: 39

Text #19

Max Range: 1.6573. Min Range: -1.6573

Max Act: 0.9494. Min Act: -0.0000

Data Index: 1117937 (C4 (Web Text))

Max Activating Token Index: 692