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

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

Neuron 825 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: 2.9783. Min Range: -2.9783

Max Act: 2.7459. Min Act: -0.0000

Data Index: 488393 (C4 (Web Text))

Max Activating Token Index: 193

Text #1

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.8205. Min Act: -0.0000

Data Index: 282304 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.9783. Min Act: -0.0000

Data Index: 404255 (C4 (Web Text))

Max Activating Token Index: 335

Text #3

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.7708. Min Act: -0.0000

Data Index: 1426693 (Python Code)

Max Activating Token Index: 210

Text #4

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.6433. Min Act: -0.0000

Data Index: 526171 (C4 (Web Text))

Max Activating Token Index: 842

Text #5

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.5594. Min Act: -0.0000

Data Index: 1163600 (C4 (Web Text))

Max Activating Token Index: 837

Text #6

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.5244. Min Act: -0.0000

Data Index: 893965 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.3634. Min Act: -0.0000

Data Index: 1225668 (C4 (Web Text))

Max Activating Token Index: 816

Text #8

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.2432. Min Act: -0.0000

Data Index: 1444411 (Python Code)

Max Activating Token Index: 771

Text #9

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.3530. Min Act: -0.0000

Data Index: 177716 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 2.9783. Min Range: -2.9783

Max Act: 1.8287. Min Act: -0.0000

Data Index: 1366559 (Python Code)

Max Activating Token Index: 124

Text #11

Max Range: 2.9783. Min Range: -2.9783

Max Act: 1.9943. Min Act: -0.0000

Data Index: 611784 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.0800. Min Act: -0.0000

Data Index: 1211024 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.0877. Min Act: -0.0001

Data Index: 1198998 (C4 (Web Text))

Max Activating Token Index: 342

Text #14

Max Range: 2.9783. Min Range: -2.9783

Max Act: 2.0176. Min Act: -0.0000

Data Index: 1617315 (Python Code)

Max Activating Token Index: 597

Text #15

Max Range: 2.9783. Min Range: -2.9783

Max Act: 1.7731. Min Act: -0.0000

Data Index: 1495181 (Python Code)

Max Activating Token Index: 570

Text #16

Max Range: 2.9783. Min Range: -2.9783

Max Act: 1.8647. Min Act: -0.0000

Data Index: 1182965 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 2.9783. Min Range: -2.9783

Max Act: 1.7444. Min Act: -0.0000

Data Index: 1413146 (Python Code)

Max Activating Token Index: 28

Text #18

Max Range: 2.9783. Min Range: -2.9783

Max Act: 1.5336. Min Act: -0.0000

Data Index: 156013 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 2.9783. Min Range: -2.9783

Max Act: 1.4193. Min Act: -0.0000

Data Index: 1393964 (Python Code)

Max Activating Token Index: 822