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

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

Neuron 464 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: 2.2545. Min Range: -2.2545

Max Act: 2.1556. Min Act: -0.0000

Data Index: 1073674 (C4 (Web Text))

Max Activating Token Index: 837

Text #1

Max Range: 2.2545. Min Range: -2.2545

Max Act: 2.2332. Min Act: -0.0000

Data Index: 1289385 (C4 (Web Text))

Max Activating Token Index: 98

Text #2

Max Range: 2.2545. Min Range: -2.2545

Max Act: 2.1547. Min Act: -0.0000

Data Index: 828349 (C4 (Web Text))

Max Activating Token Index: 101

Text #3

Max Range: 2.2545. Min Range: -2.2545

Max Act: 2.2545. Min Act: -0.0000

Data Index: 245124 (C4 (Web Text))

Max Activating Token Index: 619

Text #4

Max Range: 2.2545. Min Range: -2.2545

Max Act: 2.1231. Min Act: -0.0000

Data Index: 1206799 (C4 (Web Text))

Max Activating Token Index: 671

Text #5

Max Range: 2.2545. Min Range: -2.2545

Max Act: 2.0638. Min Act: -0.0000

Data Index: 1258637 (C4 (Web Text))

Max Activating Token Index: 967

Text #6

Max Range: 2.2545. Min Range: -2.2545

Max Act: 2.0004. Min Act: -0.0000

Data Index: 1175394 (C4 (Web Text))

Max Activating Token Index: 867

Text #7

Max Range: 2.2545. Min Range: -2.2545

Max Act: 2.0119. Min Act: -0.0000

Data Index: 1097018 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.8579. Min Act: -0.0000

Data Index: 1127506 (C4 (Web Text))

Max Activating Token Index: 140

Text #9

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.7720. Min Act: -0.0000

Data Index: 1213130 (C4 (Web Text))

Max Activating Token Index: 669

Text #10

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.5283. Min Act: -0.0000

Data Index: 828645 (C4 (Web Text))

Max Activating Token Index: 218

Text #11

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.7290. Min Act: -0.0000

Data Index: 1124701 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.6974. Min Act: -0.0000

Data Index: 882579 (C4 (Web Text))

Max Activating Token Index: 531

Text #13

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.6691. Min Act: -0.0000

Data Index: 95510 (C4 (Web Text))

Max Activating Token Index: 656

Text #14

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.5444. Min Act: -0.0000

Data Index: 373850 (C4 (Web Text))

Max Activating Token Index: 239

Text #15

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.6253. Min Act: -0.0000

Data Index: 1276913 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.6770. Min Act: -0.0000

Data Index: 839501 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.5677. Min Act: -0.0000

Data Index: 219380 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.5248. Min Act: -0.0000

Data Index: 117697 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 2.2545. Min Range: -2.2545

Max Act: 1.4934. Min Act: -0.0000

Data Index: 931941 (C4 (Web Text))

Max Activating Token Index: 1015