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

Dataset: The Pile

Neuron 1304 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: 1.4313. Min Range: -1.4313

Max Act: 1.4071. Min Act: -0.0000

Data Index: 1879994 (The Pile)

Max Activating Token Index: 876

Text #1

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.3071. Min Act: -0.0000

Data Index: 1145308 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.3480. Min Act: -0.0000

Data Index: 1356476 (The Pile)

Max Activating Token Index: 449

Text #3

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.4313. Min Act: -0.0000

Data Index: 566649 (The Pile)

Max Activating Token Index: 184

Text #4

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.2985. Min Act: -0.0000

Data Index: 1746651 (The Pile)

Max Activating Token Index: 130

Text #5

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.2831. Min Act: -0.0000

Data Index: 1209469 (The Pile)

Max Activating Token Index: 618

Text #6

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.1480. Min Act: -0.0000

Data Index: 1432075 (The Pile)

Max Activating Token Index: 812

Text #7

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.2141. Min Act: -0.0000

Data Index: 1230312 (The Pile)

Max Activating Token Index: 295

Text #8

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.1593. Min Act: -0.0000

Data Index: 199173 (The Pile)

Max Activating Token Index: 964

Text #9

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0738. Min Act: -0.0000

Data Index: 1882179 (The Pile)

Max Activating Token Index: 167

Text #10

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0772. Min Act: -0.0000

Data Index: 783524 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0811. Min Act: -0.0000

Data Index: 1679405 (The Pile)

Max Activating Token Index: 1019

Text #12

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.1770. Min Act: -0.0000

Data Index: 1031252 (The Pile)

Max Activating Token Index: 653

Text #13

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.1641. Min Act: -0.0000

Data Index: 1240352 (The Pile)

Max Activating Token Index: 988

Text #14

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0998. Min Act: -0.0000

Data Index: 499274 (The Pile)

Max Activating Token Index: 305

Text #15

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0318. Min Act: -0.0000

Data Index: 145216 (The Pile)

Max Activating Token Index: 107

Text #16

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0950. Min Act: -0.0000

Data Index: 1618080 (The Pile)

Max Activating Token Index: 228

Text #17

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.1417. Min Act: -0.0000

Data Index: 1624912 (The Pile)

Max Activating Token Index: 874

Text #18

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.1049. Min Act: -0.0000

Data Index: 1713368 (The Pile)

Max Activating Token Index: 648

Text #19

Max Range: 1.4313. Min Range: -1.4313

Max Act: 1.0619. Min Act: -0.0000

Data Index: 941083 (The Pile)

Max Activating Token Index: 345