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

Dataset: The Pile

Neuron 706 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: 1.8060. Min Range: -1.8060

Max Act: 1.8060. Min Act: -0.0000

Data Index: 992655 (The Pile)

Max Activating Token Index: 611

Text #1

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1376894 (The Pile)

Max Activating Token Index: 263

Text #2

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.5166. Min Act: -0.0000

Data Index: 1624763 (The Pile)

Max Activating Token Index: 653

Text #3

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4216. Min Act: -0.0000

Data Index: 161269 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4789. Min Act: -0.0000

Data Index: 1740806 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.3986. Min Act: -0.0000

Data Index: 1168024 (The Pile)

Max Activating Token Index: 176

Text #6

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4682. Min Act: -0.0000

Data Index: 1715801 (The Pile)

Max Activating Token Index: 653

Text #7

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.3311. Min Act: -0.0000

Data Index: 678266 (The Pile)

Max Activating Token Index: 473

Text #8

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1559. Min Act: -0.0000

Data Index: 870281 (The Pile)

Max Activating Token Index: 437

Text #9

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.3075. Min Act: -0.0000

Data Index: 214705 (The Pile)

Max Activating Token Index: 225

Text #10

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.3286. Min Act: -0.0000

Data Index: 47188 (The Pile)

Max Activating Token Index: 154

Text #11

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1864. Min Act: -0.0000

Data Index: 1347438 (The Pile)

Max Activating Token Index: 552

Text #12

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4118. Min Act: -0.0000

Data Index: 1476414 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.4216. Min Act: -0.0000

Data Index: 1615909 (The Pile)

Max Activating Token Index: 314

Text #14

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.2416. Min Act: 0.0000

Data Index: 275127 (The Pile)

Max Activating Token Index: 288

Text #15

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.3152. Min Act: -0.0000

Data Index: 1110624 (The Pile)

Max Activating Token Index: 129

Text #16

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1532. Min Act: -0.0000

Data Index: 133381 (The Pile)

Max Activating Token Index: 660

Text #17

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.2554. Min Act: -0.0000

Data Index: 1046684 (The Pile)

Max Activating Token Index: 890

Text #18

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.1446. Min Act: -0.0000

Data Index: 247041 (The Pile)

Max Activating Token Index: 742

Text #19

Max Range: 1.8060. Min Range: -1.8060

Max Act: 1.2411. Min Act: -0.0000

Data Index: 88742 (The Pile)

Max Activating Token Index: 433