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

Dataset: The Pile

Neuron 3556 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: 1.4149. Min Range: -1.4149

Max Act: 1.3407. Min Act: -0.0000

Data Index: 1642263 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.4149. Min Act: -0.0000

Data Index: 1476725 (The Pile)

Max Activating Token Index: 92

Text #2

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.2445. Min Act: -0.0000

Data Index: 161057 (The Pile)

Max Activating Token Index: 626

Text #3

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0784. Min Act: -0.0000

Data Index: 1673926 (The Pile)

Max Activating Token Index: 462

Text #4

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1497. Min Act: -0.0000

Data Index: 814654 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1141. Min Act: -0.0000

Data Index: 915451 (The Pile)

Max Activating Token Index: 751

Text #6

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0688. Min Act: -0.0000

Data Index: 1125760 (The Pile)

Max Activating Token Index: 224

Text #7

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0933. Min Act: -0.0000

Data Index: 1883460 (The Pile)

Max Activating Token Index: 637

Text #8

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.1224. Min Act: -0.0000

Data Index: 475564 (The Pile)

Max Activating Token Index: 270

Text #9

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0690. Min Act: -0.0000

Data Index: 1149271 (The Pile)

Max Activating Token Index: 63

Text #10

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0890. Min Act: -0.0000

Data Index: 1886827 (The Pile)

Max Activating Token Index: 345

Text #11

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0367. Min Act: -0.0000

Data Index: 357723 (The Pile)

Max Activating Token Index: 283

Text #12

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0033. Min Act: -0.0000

Data Index: 1829396 (The Pile)

Max Activating Token Index: 357

Text #13

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.9320. Min Act: -0.0000

Data Index: 31278 (The Pile)

Max Activating Token Index: 973

Text #14

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0210. Min Act: -0.0000

Data Index: 59978 (The Pile)

Max Activating Token Index: 120

Text #15

Max Range: 1.4149. Min Range: -1.4149

Max Act: 1.0312. Min Act: -0.0000

Data Index: 1989996 (The Pile)

Max Activating Token Index: 955

Text #16

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.9551. Min Act: -0.0000

Data Index: 746805 (The Pile)

Max Activating Token Index: 8

Text #17

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.8024. Min Act: -0.0000

Data Index: 479386 (The Pile)

Max Activating Token Index: 619

Text #18

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.9049. Min Act: -0.0000

Data Index: 1806346 (The Pile)

Max Activating Token Index: 430

Text #19

Max Range: 1.4149. Min Range: -1.4149

Max Act: 0.9597. Min Act: -0.0000

Data Index: 1001096 (The Pile)

Max Activating Token Index: 178