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

Dataset: The Pile

Neuron 2782 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: 0.4726. Min Range: -0.4726

Max Act: 0.4726. Min Act: -0.0000

Data Index: 1380023 (The Pile)

Max Activating Token Index: 984

Text #1

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4504. Min Act: -0.0000

Data Index: 1689219 (The Pile)

Max Activating Token Index: 266

Text #2

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1630652 (The Pile)

Max Activating Token Index: 777

Text #3

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4637. Min Act: -0.0000

Data Index: 1555282 (The Pile)

Max Activating Token Index: 710

Text #4

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4292. Min Act: -0.0000

Data Index: 500300 (The Pile)

Max Activating Token Index: 177

Text #5

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4410. Min Act: -0.0000

Data Index: 1383933 (The Pile)

Max Activating Token Index: 905

Text #6

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4154. Min Act: -0.0000

Data Index: 794092 (The Pile)

Max Activating Token Index: 179

Text #7

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3859. Min Act: -0.0000

Data Index: 151420 (The Pile)

Max Activating Token Index: 670

Text #8

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3991. Min Act: -0.0000

Data Index: 555013 (The Pile)

Max Activating Token Index: 105

Text #9

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4088. Min Act: -0.0000

Data Index: 1116256 (The Pile)

Max Activating Token Index: 219

Text #10

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3936. Min Act: -0.0000

Data Index: 1821121 (The Pile)

Max Activating Token Index: 731

Text #11

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4072. Min Act: -0.0000

Data Index: 1663720 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3781. Min Act: -0.0000

Data Index: 507592 (The Pile)

Max Activating Token Index: 816

Text #13

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.4254. Min Act: -0.0000

Data Index: 1732383 (The Pile)

Max Activating Token Index: 614

Text #14

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3640. Min Act: -0.0000

Data Index: 923798 (The Pile)

Max Activating Token Index: 217

Text #15

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3803. Min Act: -0.0000

Data Index: 1550601 (The Pile)

Max Activating Token Index: 43

Text #16

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3859. Min Act: -0.0000

Data Index: 102105 (The Pile)

Max Activating Token Index: 489

Text #17

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3828. Min Act: -0.0000

Data Index: 21700 (The Pile)

Max Activating Token Index: 410

Text #18

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3964. Min Act: -0.0000

Data Index: 1163991 (The Pile)

Max Activating Token Index: 653

Text #19

Max Range: 0.4726. Min Range: -0.4726

Max Act: 0.3602. Min Act: -0.0000

Data Index: 52550 (The Pile)

Max Activating Token Index: 231