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

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

Neuron 801 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: 1.1949. Min Range: -1.1949

Max Act: 1.1949. Min Act: -0.0000

Data Index: 184890 (C4 (Web Text))

Max Activating Token Index: 719

Text #1

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0626. Min Act: -0.0000

Data Index: 188892 (C4 (Web Text))

Max Activating Token Index: 949

Text #2

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0093. Min Act: -0.0000

Data Index: 1236540 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0277. Min Act: -0.0000

Data Index: 608893 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0135. Min Act: -0.0000

Data Index: 1137093 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 1.1949. Min Range: -1.1949

Max Act: 1.0066. Min Act: -0.0000

Data Index: 817123 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9553. Min Act: -0.0000

Data Index: 229900 (C4 (Web Text))

Max Activating Token Index: 702

Text #7

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9761. Min Act: -0.0000

Data Index: 1384851 (Python Code)

Max Activating Token Index: 406

Text #8

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9618. Min Act: -0.0000

Data Index: 923270 (C4 (Web Text))

Max Activating Token Index: 547

Text #9

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8962. Min Act: -0.0000

Data Index: 30294 (C4 (Web Text))

Max Activating Token Index: 416

Text #10

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9359. Min Act: -0.0000

Data Index: 1210919 (C4 (Web Text))

Max Activating Token Index: 226

Text #11

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.9090. Min Act: -0.0000

Data Index: 1125844 (C4 (Web Text))

Max Activating Token Index: 923

Text #12

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8468. Min Act: -0.0000

Data Index: 131888 (C4 (Web Text))

Max Activating Token Index: 822

Text #13

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8698. Min Act: -0.0000

Data Index: 717388 (C4 (Web Text))

Max Activating Token Index: 128

Text #14

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8814. Min Act: -0.0000

Data Index: 724838 (C4 (Web Text))

Max Activating Token Index: 598

Text #15

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8425. Min Act: -0.0000

Data Index: 597431 (C4 (Web Text))

Max Activating Token Index: 120

Text #16

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8219. Min Act: -0.0000

Data Index: 95084 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8197. Min Act: -0.0000

Data Index: 1324763 (C4 (Web Text))

Max Activating Token Index: 976

Text #18

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8549. Min Act: -0.0000

Data Index: 1081371 (C4 (Web Text))

Max Activating Token Index: 411

Text #19

Max Range: 1.1949. Min Range: -1.1949

Max Act: 0.8442. Min Act: -0.0000

Data Index: 426377 (C4 (Web Text))

Max Activating Token Index: 334