Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 1635 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.1719. Min Act: -0.0000

Data Index: 1501394 (Python Code)

Max Activating Token Index: 129

Text #1

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9842. Min Act: -0.0000

Data Index: 1586925 (Python Code)

Max Activating Token Index: 202

Text #2

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9836. Min Act: -0.0000

Data Index: 1567486 (Python Code)

Max Activating Token Index: 32

Text #3

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1367391 (Python Code)

Max Activating Token Index: 901

Text #4

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1478084 (Python Code)

Max Activating Token Index: 29

Text #5

Max Range: 1.1719. Min Range: -1.1719

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1652567 (Python Code)

Max Activating Token Index: 276

Text #6

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9596. Min Act: -0.0000

Data Index: 1366011 (Python Code)

Max Activating Token Index: 914

Text #7

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9171. Min Act: -0.0000

Data Index: 1619470 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9183. Min Act: -0.0000

Data Index: 1622870 (Python Code)

Max Activating Token Index: 456

Text #9

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9710. Min Act: -0.0000

Data Index: 1388627 (Python Code)

Max Activating Token Index: 378

Text #10

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9388. Min Act: -0.0000

Data Index: 1414944 (Python Code)

Max Activating Token Index: 1005

Text #11

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9309. Min Act: -0.0000

Data Index: 1623136 (Python Code)

Max Activating Token Index: 937

Text #12

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.8568. Min Act: -0.0000

Data Index: 1580897 (Python Code)

Max Activating Token Index: 300

Text #13

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9283. Min Act: -0.0000

Data Index: 1412401 (Python Code)

Max Activating Token Index: 499

Text #14

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9302. Min Act: -0.0000

Data Index: 1656347 (Python Code)

Max Activating Token Index: 35

Text #15

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9155. Min Act: -0.0000

Data Index: 1391473 (Python Code)

Max Activating Token Index: 138

Text #16

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1524238 (Python Code)

Max Activating Token Index: 141

Text #17

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9068. Min Act: -0.0000

Data Index: 1602055 (Python Code)

Max Activating Token Index: 669

Text #18

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9043. Min Act: -0.0000

Data Index: 1473079 (Python Code)

Max Activating Token Index: 15

Text #19

Max Range: 1.1719. Min Range: -1.1719

Max Act: 0.9321. Min Act: -0.0000

Data Index: 1580053 (Python Code)

Max Activating Token Index: 982