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

Dataset: The Pile

Neuron 1869 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2182. Min Act: -0.0000

Data Index: 381742 (The Pile)

Max Activating Token Index: 81

Text #1

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.2015. Min Act: -0.0000

Data Index: 1142767 (The Pile)

Max Activating Token Index: 50

Text #2

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1973. Min Act: -0.0000

Data Index: 618398 (The Pile)

Max Activating Token Index: 152

Text #3

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1865. Min Act: -0.0000

Data Index: 216959 (The Pile)

Max Activating Token Index: 55

Text #4

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1616. Min Act: -0.0000

Data Index: 1968188 (The Pile)

Max Activating Token Index: 60

Text #5

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1811. Min Act: -0.0000

Data Index: 1905700 (The Pile)

Max Activating Token Index: 178

Text #6

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1821. Min Act: -0.0000

Data Index: 526774 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1656. Min Act: -0.0000

Data Index: 1609256 (The Pile)

Max Activating Token Index: 827

Text #8

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1562. Min Act: -0.0000

Data Index: 296627 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1521. Min Act: -0.0000

Data Index: 1332157 (The Pile)

Max Activating Token Index: 506

Text #10

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1433. Min Act: -0.0000

Data Index: 1651918 (The Pile)

Max Activating Token Index: 431

Text #11

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1117294 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1714. Min Act: -0.0000

Data Index: 1802266 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1677. Min Act: -0.0000

Data Index: 411891 (The Pile)

Max Activating Token Index: 141

Text #14

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1539. Min Act: -0.0000

Data Index: 341474 (The Pile)

Max Activating Token Index: 136

Text #15

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1515. Min Act: -0.0000

Data Index: 795427 (The Pile)

Max Activating Token Index: 948

Text #16

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1594. Min Act: -0.0000

Data Index: 1530262 (The Pile)

Max Activating Token Index: 505

Text #17

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1468. Min Act: -0.0000

Data Index: 983820 (The Pile)

Max Activating Token Index: 287

Text #18

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1290. Min Act: -0.0000

Data Index: 1893968 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 0.2182. Min Range: -0.2182

Max Act: 0.1230. Min Act: -0.0000

Data Index: 1046125 (The Pile)

Max Activating Token Index: 590