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

Dataset: The Pile

Neuron 2137 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0703. Min Act: -0.0000

Data Index: 1454387 (The Pile)

Max Activating Token Index: 130

Text #1

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0677. Min Act: -0.0000

Data Index: 1477694 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0673. Min Act: -0.0000

Data Index: 943044 (The Pile)

Max Activating Token Index: 114

Text #3

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0670. Min Act: -0.0000

Data Index: 284398 (The Pile)

Max Activating Token Index: 1023

Text #4

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1782772 (The Pile)

Max Activating Token Index: 602

Text #5

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0659. Min Act: -0.0000

Data Index: 346134 (The Pile)

Max Activating Token Index: 163

Text #6

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0659. Min Act: -0.0000

Data Index: 1967376 (The Pile)

Max Activating Token Index: 449

Text #7

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0660. Min Act: -0.0000

Data Index: 1877529 (The Pile)

Max Activating Token Index: 1019

Text #8

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0655. Min Act: -0.0000

Data Index: 502725 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0652. Min Act: -0.0000

Data Index: 841722 (The Pile)

Max Activating Token Index: 1020

Text #10

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0654. Min Act: -0.0000

Data Index: 119283 (The Pile)

Max Activating Token Index: 967

Text #11

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0642. Min Act: -0.0000

Data Index: 727412 (The Pile)

Max Activating Token Index: 980

Text #12

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1139729 (The Pile)

Max Activating Token Index: 1019

Text #13

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0641. Min Act: -0.0000

Data Index: 1505821 (The Pile)

Max Activating Token Index: 944

Text #14

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0644. Min Act: -0.0000

Data Index: 1230182 (The Pile)

Max Activating Token Index: 271

Text #15

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0641. Min Act: -0.0000

Data Index: 381508 (The Pile)

Max Activating Token Index: 980

Text #16

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0664. Min Act: -0.0000

Data Index: 329797 (The Pile)

Max Activating Token Index: 207

Text #17

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1787769 (The Pile)

Max Activating Token Index: 1022

Text #18

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0638. Min Act: -0.0000

Data Index: 866933 (The Pile)

Max Activating Token Index: 809

Text #19

Max Range: 0.0703. Min Range: -0.0703

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1811271 (The Pile)

Max Activating Token Index: 864