Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 686 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.6466. Min Act: -0.0000

Data Index: 1623248 (Python Code)

Max Activating Token Index: 678

Text #1

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.3430. Min Act: -0.0000

Data Index: 1547922 (Python Code)

Max Activating Token Index: 890

Text #2

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.3028. Min Act: -0.0000

Data Index: 1510995 (Python Code)

Max Activating Token Index: 24

Text #3

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.2816. Min Act: -0.0001

Data Index: 334866 (C4 (Web Text))

Max Activating Token Index: 661

Text #4

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1697. Min Act: -0.0000

Data Index: 18096 (C4 (Web Text))

Max Activating Token Index: 602

Text #5

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1569. Min Act: -0.0000

Data Index: 1188924 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1815. Min Act: -0.0001

Data Index: 491048 (C4 (Web Text))

Max Activating Token Index: 554

Text #7

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1654. Min Act: -0.0000

Data Index: 1392623 (Python Code)

Max Activating Token Index: 818

Text #8

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1575. Min Act: -0.0001

Data Index: 557515 (C4 (Web Text))

Max Activating Token Index: 434

Text #9

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1925. Min Act: -0.0001

Data Index: 497755 (C4 (Web Text))

Max Activating Token Index: 292

Text #10

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1505. Min Act: -0.0000

Data Index: 1597159 (Python Code)

Max Activating Token Index: 845

Text #11

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1215. Min Act: -0.0001

Data Index: 1417625 (Python Code)

Max Activating Token Index: 302

Text #12

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1472. Min Act: -0.0000

Data Index: 1563004 (Python Code)

Max Activating Token Index: 494

Text #13

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1135908 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1649. Min Act: -0.0000

Data Index: 1121304 (C4 (Web Text))

Max Activating Token Index: 425

Text #15

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.0597. Min Act: -0.0000

Data Index: 1281108 (C4 (Web Text))

Max Activating Token Index: 202

Text #16

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1211. Min Act: -0.0000

Data Index: 1357836 (C4 (Web Text))

Max Activating Token Index: 596

Text #17

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1071. Min Act: -0.0000

Data Index: 1419891 (Python Code)

Max Activating Token Index: 283

Text #18

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.0842. Min Act: -0.0000

Data Index: 1569311 (Python Code)

Max Activating Token Index: 616

Text #19

Max Range: 1.6466. Min Range: -1.6466

Max Act: 1.1148. Min Act: -0.0001

Data Index: 1454630 (Python Code)

Max Activating Token Index: 240