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

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

Neuron 4496 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.6125. Min Act: -0.0000

Data Index: 1341684 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.4937. Min Act: -0.0000

Data Index: 82491 (C4 (Web Text))

Max Activating Token Index: 71

Text #2

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.3310. Min Act: -0.0000

Data Index: 1273121 (C4 (Web Text))

Max Activating Token Index: 255

Text #3

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.4845. Min Act: -0.0000

Data Index: 1352746 (C4 (Web Text))

Max Activating Token Index: 807

Text #4

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.2401. Min Act: -0.0000

Data Index: 1131403 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.4968. Min Act: -0.0000

Data Index: 738440 (C4 (Web Text))

Max Activating Token Index: 817

Text #6

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.4618. Min Act: -0.0000

Data Index: 492199 (C4 (Web Text))

Max Activating Token Index: 516

Text #7

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.3385. Min Act: -0.0000

Data Index: 811745 (C4 (Web Text))

Max Activating Token Index: 492

Text #8

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.3177. Min Act: -0.0000

Data Index: 995512 (C4 (Web Text))

Max Activating Token Index: 380

Text #9

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.3120. Min Act: -0.0000

Data Index: 1168789 (C4 (Web Text))

Max Activating Token Index: 570

Text #10

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.2844. Min Act: -0.0000

Data Index: 1002496 (C4 (Web Text))

Max Activating Token Index: 672

Text #11

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.2633. Min Act: -0.0000

Data Index: 483064 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.2684. Min Act: -0.0000

Data Index: 253535 (C4 (Web Text))

Max Activating Token Index: 140

Text #13

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.2552. Min Act: -0.0000

Data Index: 354302 (C4 (Web Text))

Max Activating Token Index: 888

Text #14

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.2580. Min Act: -0.0000

Data Index: 1490208 (Python Code)

Max Activating Token Index: 211

Text #15

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.2281. Min Act: -0.0000

Data Index: 375363 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.2216. Min Act: -0.0000

Data Index: 81360 (C4 (Web Text))

Max Activating Token Index: 342

Text #17

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.1088. Min Act: -0.0000

Data Index: 1022480 (C4 (Web Text))

Max Activating Token Index: 250

Text #18

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.1787. Min Act: -0.0000

Data Index: 345703 (C4 (Web Text))

Max Activating Token Index: 863

Text #19

Max Range: 2.6125. Min Range: -2.6125

Max Act: 2.1136. Min Act: -0.0000

Data Index: 322010 (C4 (Web Text))

Max Activating Token Index: 122