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

Dataset: The Pile

Neuron 2735 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.8211. Min Act: -0.0000

Data Index: 1144176 (The Pile)

Max Activating Token Index: 554

Text #1

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.7194. Min Act: -0.0000

Data Index: 957856 (The Pile)

Max Activating Token Index: 219

Text #2

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6687. Min Act: -0.0000

Data Index: 322367 (The Pile)

Max Activating Token Index: 179

Text #3

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1556044 (The Pile)

Max Activating Token Index: 221

Text #4

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6282. Min Act: -0.0000

Data Index: 651775 (The Pile)

Max Activating Token Index: 481

Text #5

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6306. Min Act: -0.0000

Data Index: 22633 (The Pile)

Max Activating Token Index: 125

Text #6

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6546. Min Act: -0.0000

Data Index: 1640426 (The Pile)

Max Activating Token Index: 73

Text #7

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5861. Min Act: -0.0000

Data Index: 1193234 (The Pile)

Max Activating Token Index: 216

Text #8

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6081. Min Act: -0.0000

Data Index: 1786551 (The Pile)

Max Activating Token Index: 1010

Text #9

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5736. Min Act: -0.0000

Data Index: 1343066 (The Pile)

Max Activating Token Index: 956

Text #10

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6055. Min Act: -0.0000

Data Index: 579394 (The Pile)

Max Activating Token Index: 67

Text #11

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6627. Min Act: -0.0000

Data Index: 1436817 (The Pile)

Max Activating Token Index: 164

Text #12

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6180. Min Act: -0.0000

Data Index: 1940951 (The Pile)

Max Activating Token Index: 13

Text #13

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6433. Min Act: -0.0000

Data Index: 1381317 (The Pile)

Max Activating Token Index: 863

Text #14

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5575. Min Act: -0.0000

Data Index: 443305 (The Pile)

Max Activating Token Index: 207

Text #15

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6228. Min Act: -0.0000

Data Index: 935692 (The Pile)

Max Activating Token Index: 437

Text #16

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6200. Min Act: -0.0000

Data Index: 739050 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1818135 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5811. Min Act: -0.0000

Data Index: 337229 (The Pile)

Max Activating Token Index: 292

Text #19

Max Range: 0.8211. Min Range: -0.8211

Max Act: 0.5947. Min Act: -0.0000

Data Index: 1521465 (The Pile)

Max Activating Token Index: 171