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

Dataset: The Pile

Neuron 1860 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.2705. Min Act: -0.0000

Data Index: 1903783 (The Pile)

Max Activating Token Index: 677

Text #1

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1144. Min Act: -0.0000

Data Index: 1162563 (The Pile)

Max Activating Token Index: 108

Text #2

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0715. Min Act: -0.0000

Data Index: 978203 (The Pile)

Max Activating Token Index: 637

Text #3

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.1479. Min Act: -0.0000

Data Index: 1696569 (The Pile)

Max Activating Token Index: 22

Text #4

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.9848. Min Act: -0.0000

Data Index: 551147 (The Pile)

Max Activating Token Index: 911

Text #5

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.9767. Min Act: -0.0000

Data Index: 557759 (The Pile)

Max Activating Token Index: 284

Text #6

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.7534. Min Act: -0.0000

Data Index: 1009682 (The Pile)

Max Activating Token Index: 796

Text #7

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0163. Min Act: -0.0000

Data Index: 1620407 (The Pile)

Max Activating Token Index: 756

Text #8

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.8606. Min Act: -0.0000

Data Index: 1043436 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.6794. Min Act: -0.0000

Data Index: 885291 (The Pile)

Max Activating Token Index: 818

Text #10

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.8191. Min Act: -0.0000

Data Index: 271100 (The Pile)

Max Activating Token Index: 133

Text #11

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.9556. Min Act: -0.0000

Data Index: 1781118 (The Pile)

Max Activating Token Index: 357

Text #12

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0952. Min Act: -0.0000

Data Index: 1410697 (The Pile)

Max Activating Token Index: 530

Text #13

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.5386. Min Act: -0.0000

Data Index: 1960058 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.8168. Min Act: -0.0000

Data Index: 205000 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 3.2705. Min Range: -3.2705

Max Act: 3.0311. Min Act: -0.0000

Data Index: 1123749 (The Pile)

Max Activating Token Index: 675

Text #16

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.8836. Min Act: -0.0000

Data Index: 1810757 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.5829. Min Act: -0.0000

Data Index: 1411709 (The Pile)

Max Activating Token Index: 47

Text #18

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.8466. Min Act: -0.0000

Data Index: 1806563 (The Pile)

Max Activating Token Index: 908

Text #19

Max Range: 3.2705. Min Range: -3.2705

Max Act: 2.9922. Min Act: -0.0000

Data Index: 993429 (The Pile)

Max Activating Token Index: 40