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

Dataset: The Pile

Neuron 1102 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1244. Min Range: -1.1244

Max Act: 1.1244. Min Act: -0.0000

Data Index: 1851900 (The Pile)

Max Activating Token Index: 18

Text #1

Max Range: 1.1244. Min Range: -1.1244

Max Act: 1.0473. Min Act: -0.0000

Data Index: 1508269 (The Pile)

Max Activating Token Index: 486

Text #2

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9822. Min Act: -0.0000

Data Index: 1452252 (The Pile)

Max Activating Token Index: 13

Text #3

Max Range: 1.1244. Min Range: -1.1244

Max Act: 1.0366. Min Act: -0.0000

Data Index: 1232183 (The Pile)

Max Activating Token Index: 66

Text #4

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8733. Min Act: -0.0000

Data Index: 1458982 (The Pile)

Max Activating Token Index: 646

Text #5

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1115276 (The Pile)

Max Activating Token Index: 718

Text #6

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9415. Min Act: -0.0000

Data Index: 274085 (The Pile)

Max Activating Token Index: 192

Text #7

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1250970 (The Pile)

Max Activating Token Index: 766

Text #8

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.9741. Min Act: -0.0000

Data Index: 315249 (The Pile)

Max Activating Token Index: 917

Text #9

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8671. Min Act: 0.0000

Data Index: 920185 (The Pile)

Max Activating Token Index: 81

Text #10

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8518. Min Act: -0.0000

Data Index: 85587 (The Pile)

Max Activating Token Index: 399

Text #11

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8773. Min Act: -0.0000

Data Index: 746375 (The Pile)

Max Activating Token Index: 292

Text #12

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1107030 (The Pile)

Max Activating Token Index: 374

Text #13

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8883. Min Act: -0.0000

Data Index: 1902062 (The Pile)

Max Activating Token Index: 120

Text #14

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8380. Min Act: 0.0000

Data Index: 316000 (The Pile)

Max Activating Token Index: 197

Text #15

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8009. Min Act: -0.0000

Data Index: 1366734 (The Pile)

Max Activating Token Index: 882

Text #16

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8506. Min Act: -0.0000

Data Index: 799280 (The Pile)

Max Activating Token Index: 782

Text #17

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8269. Min Act: -0.0000

Data Index: 493024 (The Pile)

Max Activating Token Index: 295

Text #18

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8582. Min Act: -0.0000

Data Index: 825277 (The Pile)

Max Activating Token Index: 97

Text #19

Max Range: 1.1244. Min Range: -1.1244

Max Act: 0.8017. Min Act: -0.0000

Data Index: 229367 (The Pile)

Max Activating Token Index: 235