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

Dataset: The Pile

Neuron 1760 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.8221. Min Act: -0.0000

Data Index: 1181061 (The Pile)

Max Activating Token Index: 774

Text #1

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.7176. Min Act: -0.0000

Data Index: 1144695 (The Pile)

Max Activating Token Index: 835

Text #2

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.7144. Min Act: -0.0000

Data Index: 324865 (The Pile)

Max Activating Token Index: 77

Text #3

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6641. Min Act: -0.0000

Data Index: 232949 (The Pile)

Max Activating Token Index: 695

Text #4

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1900890 (The Pile)

Max Activating Token Index: 751

Text #5

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6932. Min Act: -0.0000

Data Index: 148865 (The Pile)

Max Activating Token Index: 1005

Text #6

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6982. Min Act: -0.0000

Data Index: 1541806 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6359. Min Act: -0.0000

Data Index: 963979 (The Pile)

Max Activating Token Index: 925

Text #8

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6536. Min Act: -0.0000

Data Index: 899051 (The Pile)

Max Activating Token Index: 537

Text #9

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6904. Min Act: -0.0000

Data Index: 404812 (The Pile)

Max Activating Token Index: 481

Text #10

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1377569 (The Pile)

Max Activating Token Index: 593

Text #11

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6441. Min Act: -0.0000

Data Index: 54698 (The Pile)

Max Activating Token Index: 308

Text #12

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1009848 (The Pile)

Max Activating Token Index: 759

Text #13

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6169. Min Act: -0.0000

Data Index: 59442 (The Pile)

Max Activating Token Index: 830

Text #14

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6638. Min Act: -0.0000

Data Index: 242853 (The Pile)

Max Activating Token Index: 68

Text #15

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6161. Min Act: -0.0000

Data Index: 405958 (The Pile)

Max Activating Token Index: 622

Text #16

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.5553. Min Act: -0.0000

Data Index: 643906 (The Pile)

Max Activating Token Index: 592

Text #17

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6341. Min Act: -0.0000

Data Index: 600426 (The Pile)

Max Activating Token Index: 721

Text #18

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6105. Min Act: -0.0000

Data Index: 16133 (The Pile)

Max Activating Token Index: 398

Text #19

Max Range: 0.8221. Min Range: -0.8221

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1187613 (The Pile)

Max Activating Token Index: 685