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

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

Neuron 2591 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.3768. Min Range: -2.3768

Max Act: 2.3768. Min Act: -0.0000

Data Index: 1078033 (C4 (Web Text))

Max Activating Token Index: 766

Text #1

Max Range: 2.3768. Min Range: -2.3768

Max Act: 2.2631. Min Act: -0.0000

Data Index: 183752 (C4 (Web Text))

Max Activating Token Index: 905

Text #2

Max Range: 2.3768. Min Range: -2.3768

Max Act: 2.1173. Min Act: -0.0000

Data Index: 1285094 (C4 (Web Text))

Max Activating Token Index: 877

Text #3

Max Range: 2.3768. Min Range: -2.3768

Max Act: 2.3516. Min Act: -0.0000

Data Index: 1247826 (C4 (Web Text))

Max Activating Token Index: 801

Text #4

Max Range: 2.3768. Min Range: -2.3768

Max Act: 2.1951. Min Act: -0.0000

Data Index: 979084 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 2.3768. Min Range: -2.3768

Max Act: 2.1715. Min Act: -0.0000

Data Index: 513992 (C4 (Web Text))

Max Activating Token Index: 415

Text #6

Max Range: 2.3768. Min Range: -2.3768

Max Act: 2.2456. Min Act: -0.0000

Data Index: 16010 (C4 (Web Text))

Max Activating Token Index: 969

Text #7

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.9479. Min Act: -0.0000

Data Index: 1329231 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 2.3768. Min Range: -2.3768

Max Act: 2.0439. Min Act: -0.0000

Data Index: 1120074 (C4 (Web Text))

Max Activating Token Index: 969

Text #9

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.9638. Min Act: -0.0000

Data Index: 809115 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.9543. Min Act: -0.0000

Data Index: 650847 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.9432. Min Act: -0.0000

Data Index: 1083454 (C4 (Web Text))

Max Activating Token Index: 855

Text #12

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.7287. Min Act: -0.0000

Data Index: 577002 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.8074. Min Act: -0.0000

Data Index: 564144 (C4 (Web Text))

Max Activating Token Index: 109

Text #14

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.8949. Min Act: -0.0000

Data Index: 743932 (C4 (Web Text))

Max Activating Token Index: 395

Text #15

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.9863. Min Act: -0.0000

Data Index: 286439 (C4 (Web Text))

Max Activating Token Index: 576

Text #16

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.9001. Min Act: -0.0000

Data Index: 809642 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.9570. Min Act: -0.0000

Data Index: 709209 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.9235. Min Act: -0.0000

Data Index: 700200 (C4 (Web Text))

Max Activating Token Index: 486

Text #19

Max Range: 2.3768. Min Range: -2.3768

Max Act: 1.7070. Min Act: -0.0000

Data Index: 536851 (C4 (Web Text))

Max Activating Token Index: 840