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

Dataset: The Pile

Neuron 332 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: 1.1313. Min Range: -1.1313

Max Act: 1.1095. Min Act: -0.0000

Data Index: 250183 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.1313. Min Act: -0.0000

Data Index: 579128 (The Pile)

Max Activating Token Index: 709

Text #2

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.1185. Min Act: -0.0000

Data Index: 816241 (The Pile)

Max Activating Token Index: 186

Text #3

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1220924 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0377. Min Act: -0.0000

Data Index: 1209998 (The Pile)

Max Activating Token Index: 304

Text #5

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.1170. Min Act: -0.0000

Data Index: 34842 (The Pile)

Max Activating Token Index: 1022

Text #6

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0896. Min Act: -0.0000

Data Index: 1688097 (The Pile)

Max Activating Token Index: 550

Text #7

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0398. Min Act: -0.0000

Data Index: 1031536 (The Pile)

Max Activating Token Index: 266

Text #8

Max Range: 1.1313. Min Range: -1.1313

Max Act: 1.0495. Min Act: -0.0000

Data Index: 1397746 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9488. Min Act: -0.0000

Data Index: 827208 (The Pile)

Max Activating Token Index: 989

Text #10

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9874. Min Act: -0.0000

Data Index: 494961 (The Pile)

Max Activating Token Index: 45

Text #11

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9594. Min Act: -0.0000

Data Index: 19797 (The Pile)

Max Activating Token Index: 323

Text #12

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9372. Min Act: -0.0000

Data Index: 1264794 (The Pile)

Max Activating Token Index: 323

Text #13

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9902. Min Act: -0.0000

Data Index: 326922 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.8594. Min Act: -0.0000

Data Index: 1705190 (The Pile)

Max Activating Token Index: 478

Text #15

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1650394 (The Pile)

Max Activating Token Index: 478

Text #16

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9543. Min Act: -0.0000

Data Index: 1001445 (The Pile)

Max Activating Token Index: 105

Text #17

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9588. Min Act: -0.0000

Data Index: 240092 (The Pile)

Max Activating Token Index: 906

Text #18

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9401. Min Act: -0.0000

Data Index: 1580480 (The Pile)

Max Activating Token Index: 492

Text #19

Max Range: 1.1313. Min Range: -1.1313

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1328646 (The Pile)

Max Activating Token Index: 221