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

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

Neuron 4593 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.7713. Min Act: -0.0000

Data Index: 740353 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.6617. Min Act: -0.0000

Data Index: 195378 (C4 (Web Text))

Max Activating Token Index: 416

Text #2

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.6552. Min Act: -0.0000

Data Index: 525010 (C4 (Web Text))

Max Activating Token Index: 560

Text #3

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.6252. Min Act: -0.0000

Data Index: 13499 (C4 (Web Text))

Max Activating Token Index: 436

Text #4

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.5962. Min Act: -0.0000

Data Index: 657349 (C4 (Web Text))

Max Activating Token Index: 562

Text #5

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.5648. Min Act: -0.0000

Data Index: 696009 (C4 (Web Text))

Max Activating Token Index: 708

Text #6

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4990. Min Act: -0.0000

Data Index: 375927 (C4 (Web Text))

Max Activating Token Index: 153

Text #7

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.5015. Min Act: -0.0000

Data Index: 866638 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4848. Min Act: -0.0000

Data Index: 146398 (C4 (Web Text))

Max Activating Token Index: 616

Text #9

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4806. Min Act: -0.0000

Data Index: 232927 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4696. Min Act: 0.0000

Data Index: 1303015 (C4 (Web Text))

Max Activating Token Index: 411

Text #11

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4669. Min Act: -0.0000

Data Index: 982511 (C4 (Web Text))

Max Activating Token Index: 588

Text #12

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4484. Min Act: -0.0000

Data Index: 198387 (C4 (Web Text))

Max Activating Token Index: 771

Text #13

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4594. Min Act: -0.0000

Data Index: 565910 (C4 (Web Text))

Max Activating Token Index: 502

Text #14

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4270. Min Act: 0.0001

Data Index: 562412 (C4 (Web Text))

Max Activating Token Index: 855

Text #15

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4280. Min Act: -0.0000

Data Index: 959825 (C4 (Web Text))

Max Activating Token Index: 653

Text #16

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4231. Min Act: -0.0000

Data Index: 477664 (C4 (Web Text))

Max Activating Token Index: 975

Text #17

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4235. Min Act: -0.0000

Data Index: 194213 (C4 (Web Text))

Max Activating Token Index: 84

Text #18

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4333. Min Act: -0.0000

Data Index: 1273045 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.7713. Min Range: -0.7713

Max Act: 0.4163. Min Act: -0.0000

Data Index: 989655 (C4 (Web Text))

Max Activating Token Index: 838