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

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

Neuron 5927 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: 0.9561. Min Range: -0.9561

Max Act: 0.8911. Min Act: -0.0000

Data Index: 113826 (C4 (Web Text))

Max Activating Token Index: 428

Text #1

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1347767 (C4 (Web Text))

Max Activating Token Index: 666

Text #2

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8731. Min Act: -0.0000

Data Index: 338751 (C4 (Web Text))

Max Activating Token Index: 96

Text #3

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8157. Min Act: -0.0000

Data Index: 647239 (C4 (Web Text))

Max Activating Token Index: 824

Text #4

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8470. Min Act: -0.0000

Data Index: 963258 (C4 (Web Text))

Max Activating Token Index: 756

Text #5

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8630. Min Act: -0.0000

Data Index: 243860 (C4 (Web Text))

Max Activating Token Index: 651

Text #6

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8333. Min Act: -0.0000

Data Index: 796441 (C4 (Web Text))

Max Activating Token Index: 811

Text #7

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8173. Min Act: -0.0000

Data Index: 1041245 (C4 (Web Text))

Max Activating Token Index: 342

Text #8

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7889. Min Act: -0.0000

Data Index: 944195 (C4 (Web Text))

Max Activating Token Index: 755

Text #9

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8134. Min Act: -0.0000

Data Index: 697262 (C4 (Web Text))

Max Activating Token Index: 937

Text #10

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7686. Min Act: -0.0000

Data Index: 808423 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.8201. Min Act: -0.0000

Data Index: 846264 (C4 (Web Text))

Max Activating Token Index: 830

Text #12

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7904. Min Act: -0.0000

Data Index: 90948 (C4 (Web Text))

Max Activating Token Index: 837

Text #13

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7663. Min Act: -0.0000

Data Index: 957223 (C4 (Web Text))

Max Activating Token Index: 525

Text #14

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7712. Min Act: -0.0000

Data Index: 820795 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7721. Min Act: -0.0000

Data Index: 636621 (C4 (Web Text))

Max Activating Token Index: 774

Text #16

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7044. Min Act: -0.0000

Data Index: 1351636 (C4 (Web Text))

Max Activating Token Index: 181

Text #17

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.6929. Min Act: -0.0000

Data Index: 476196 (C4 (Web Text))

Max Activating Token Index: 631

Text #18

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7317. Min Act: -0.0000

Data Index: 948826 (C4 (Web Text))

Max Activating Token Index: 374

Text #19

Max Range: 0.9561. Min Range: -0.9561

Max Act: 0.7058. Min Act: -0.0000

Data Index: 289129 (C4 (Web Text))

Max Activating Token Index: 981