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

Dataset: The Pile

Neuron 754 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: 0.6379. Min Range: -0.6379

Max Act: 0.6133. Min Act: -0.0000

Data Index: 379975 (The Pile)

Max Activating Token Index: 471

Text #1

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1594749 (The Pile)

Max Activating Token Index: 849

Text #2

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5552. Min Act: -0.0000

Data Index: 1342180 (The Pile)

Max Activating Token Index: 138

Text #3

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6379. Min Act: -0.0000

Data Index: 1157437 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5994. Min Act: -0.0000

Data Index: 1084868 (The Pile)

Max Activating Token Index: 85

Text #5

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5604. Min Act: 0.0000

Data Index: 284572 (The Pile)

Max Activating Token Index: 46

Text #6

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5603. Min Act: -0.0000

Data Index: 530430 (The Pile)

Max Activating Token Index: 982

Text #7

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5014. Min Act: 0.0000

Data Index: 538486 (The Pile)

Max Activating Token Index: 82

Text #8

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1729709 (The Pile)

Max Activating Token Index: 563

Text #9

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5573. Min Act: -0.0000

Data Index: 296900 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4990. Min Act: -0.0000

Data Index: 102260 (The Pile)

Max Activating Token Index: 875

Text #11

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5280. Min Act: -0.0000

Data Index: 794535 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5917. Min Act: -0.0000

Data Index: 1744983 (The Pile)

Max Activating Token Index: 74

Text #13

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5546. Min Act: 0.0000

Data Index: 235781 (The Pile)

Max Activating Token Index: 601

Text #14

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5774. Min Act: -0.0000

Data Index: 620438 (The Pile)

Max Activating Token Index: 97

Text #15

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5036. Min Act: 0.0000

Data Index: 1029909 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5196. Min Act: 0.0000

Data Index: 1472807 (The Pile)

Max Activating Token Index: 47

Text #17

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.4656. Min Act: -0.0000

Data Index: 1359793 (The Pile)

Max Activating Token Index: 944

Text #18

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.5165. Min Act: 0.0000

Data Index: 1801331 (The Pile)

Max Activating Token Index: 315

Text #19

Max Range: 0.6379. Min Range: -0.6379

Max Act: 0.6130. Min Act: -0.0000

Data Index: 1540835 (The Pile)

Max Activating Token Index: 378