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

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

Neuron 340 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8912. Min Range: -2.8912

Max Act: 2.8912. Min Act: -0.0000

Data Index: 1013956 (C4 (Web Text))

Max Activating Token Index: 441

Text #1

Max Range: 2.8912. Min Range: -2.8912

Max Act: 2.1105. Min Act: -0.0000

Data Index: 985497 (C4 (Web Text))

Max Activating Token Index: 704

Text #2

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.9900. Min Act: -0.0000

Data Index: 652315 (C4 (Web Text))

Max Activating Token Index: 232

Text #3

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.9196. Min Act: -0.0000

Data Index: 998878 (C4 (Web Text))

Max Activating Token Index: 758

Text #4

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.8651. Min Act: -0.0000

Data Index: 841383 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.8467. Min Act: -0.0000

Data Index: 509608 (C4 (Web Text))

Max Activating Token Index: 150

Text #6

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.8065. Min Act: -0.0000

Data Index: 512767 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.7528. Min Act: -0.0000

Data Index: 810168 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.8306. Min Act: -0.0000

Data Index: 699029 (C4 (Web Text))

Max Activating Token Index: 664

Text #9

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.6404. Min Act: -0.0000

Data Index: 225533 (C4 (Web Text))

Max Activating Token Index: 480

Text #10

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.7007. Min Act: -0.0000

Data Index: 43722 (C4 (Web Text))

Max Activating Token Index: 499

Text #11

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.6343. Min Act: -0.0000

Data Index: 211799 (C4 (Web Text))

Max Activating Token Index: 525

Text #12

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.6905. Min Act: -0.0000

Data Index: 628883 (C4 (Web Text))

Max Activating Token Index: 199

Text #13

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.5681. Min Act: -0.0000

Data Index: 384130 (C4 (Web Text))

Max Activating Token Index: 428

Text #14

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.5067. Min Act: -0.0000

Data Index: 84840 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.5014. Min Act: -0.0000

Data Index: 494040 (C4 (Web Text))

Max Activating Token Index: 694

Text #16

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.5018. Min Act: -0.0000

Data Index: 905894 (C4 (Web Text))

Max Activating Token Index: 759

Text #17

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.5773. Min Act: -0.0000

Data Index: 104902 (C4 (Web Text))

Max Activating Token Index: 811

Text #18

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.4873. Min Act: -0.0000

Data Index: 870942 (C4 (Web Text))

Max Activating Token Index: 844

Text #19

Max Range: 2.8912. Min Range: -2.8912

Max Act: 1.3829. Min Act: -0.0000

Data Index: 839112 (C4 (Web Text))

Max Activating Token Index: 361