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

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

Neuron 316 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.3776. Min Act: -0.0000

Data Index: 1233495 (C4 (Web Text))

Max Activating Token Index: 846

Text #1

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0523. Min Act: -0.0000

Data Index: 1073349 (C4 (Web Text))

Max Activating Token Index: 491

Text #2

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0427. Min Act: -0.0000

Data Index: 384614 (C4 (Web Text))

Max Activating Token Index: 808

Text #3

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0118. Min Act: -0.0000

Data Index: 528467 (C4 (Web Text))

Max Activating Token Index: 76

Text #4

Max Range: 1.3776. Min Range: -1.3776

Max Act: 1.0214. Min Act: -0.0000

Data Index: 1316990 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9389. Min Act: -0.0000

Data Index: 523903 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9989. Min Act: -0.0000

Data Index: 15859 (C4 (Web Text))

Max Activating Token Index: 593

Text #7

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9110. Min Act: -0.0000

Data Index: 878212 (C4 (Web Text))

Max Activating Token Index: 580

Text #8

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9612. Min Act: -0.0000

Data Index: 1416706 (Python Code)

Max Activating Token Index: 140

Text #9

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9432. Min Act: -0.0000

Data Index: 129176 (C4 (Web Text))

Max Activating Token Index: 233

Text #10

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9507. Min Act: -0.0000

Data Index: 872589 (C4 (Web Text))

Max Activating Token Index: 573

Text #11

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.8262. Min Act: -0.0000

Data Index: 587623 (C4 (Web Text))

Max Activating Token Index: 825

Text #12

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.8360. Min Act: -0.0000

Data Index: 234597 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.8665. Min Act: -0.0000

Data Index: 1266922 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.8940. Min Act: -0.0000

Data Index: 1200547 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.8310. Min Act: -0.0000

Data Index: 921936 (C4 (Web Text))

Max Activating Token Index: 477

Text #16

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.7692. Min Act: -0.0000

Data Index: 381897 (C4 (Web Text))

Max Activating Token Index: 865

Text #17

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.8362. Min Act: -0.0000

Data Index: 157228 (C4 (Web Text))

Max Activating Token Index: 348

Text #18

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.9093. Min Act: -0.0000

Data Index: 778911 (C4 (Web Text))

Max Activating Token Index: 151

Text #19

Max Range: 1.3776. Min Range: -1.3776

Max Act: 0.7612. Min Act: -0.0000

Data Index: 280849 (C4 (Web Text))

Max Activating Token Index: 180