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

Dataset: The Pile

Neuron 1779 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: 0.2191. Min Range: -0.2191

Max Act: 0.2154. Min Act: -0.0000

Data Index: 796235 (The Pile)

Max Activating Token Index: 98

Text #1

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.2172. Min Act: -0.0000

Data Index: 1127517 (The Pile)

Max Activating Token Index: 524

Text #2

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.2191. Min Act: -0.0000

Data Index: 1320757 (The Pile)

Max Activating Token Index: 274

Text #3

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.2063. Min Act: -0.0000

Data Index: 1838898 (The Pile)

Max Activating Token Index: 959

Text #4

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1979. Min Act: -0.0000

Data Index: 1543261 (The Pile)

Max Activating Token Index: 324

Text #5

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1873. Min Act: -0.0000

Data Index: 1104358 (The Pile)

Max Activating Token Index: 347

Text #6

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1863. Min Act: -0.0000

Data Index: 1763655 (The Pile)

Max Activating Token Index: 348

Text #7

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1790. Min Act: -0.0000

Data Index: 210631 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1900. Min Act: -0.0000

Data Index: 1493429 (The Pile)

Max Activating Token Index: 314

Text #9

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1776. Min Act: -0.0000

Data Index: 1722267 (The Pile)

Max Activating Token Index: 741

Text #10

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1833. Min Act: -0.0000

Data Index: 771864 (The Pile)

Max Activating Token Index: 167

Text #11

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1907. Min Act: -0.0000

Data Index: 1339080 (The Pile)

Max Activating Token Index: 459

Text #12

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1820. Min Act: -0.0000

Data Index: 1983639 (The Pile)

Max Activating Token Index: 311

Text #13

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1936. Min Act: -0.0000

Data Index: 409863 (The Pile)

Max Activating Token Index: 737

Text #14

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1722. Min Act: -0.0000

Data Index: 161341 (The Pile)

Max Activating Token Index: 527

Text #15

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1751. Min Act: -0.0000

Data Index: 756634 (The Pile)

Max Activating Token Index: 511

Text #16

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1752. Min Act: 0.0000

Data Index: 491887 (The Pile)

Max Activating Token Index: 81

Text #17

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1726. Min Act: -0.0000

Data Index: 300804 (The Pile)

Max Activating Token Index: 986

Text #18

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1735. Min Act: -0.0000

Data Index: 172970 (The Pile)

Max Activating Token Index: 850

Text #19

Max Range: 0.2191. Min Range: -0.2191

Max Act: 0.1769. Min Act: -0.0000

Data Index: 1770702 (The Pile)

Max Activating Token Index: 769