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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 87 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0859. Min Act: -0.0002

Data Index: 280048 (C4 (Web Text))

Max Activating Token Index: 980

Text #1

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0792. Min Act: -0.0001

Data Index: 741318 (C4 (Web Text))

Max Activating Token Index: 573

Text #2

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0745. Min Act: -0.0001

Data Index: 633806 (C4 (Web Text))

Max Activating Token Index: 584

Text #3

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0650. Min Act: -0.0001

Data Index: 504123 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0681. Min Act: -0.0001

Data Index: 20035 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0680. Min Act: -0.0001

Data Index: 235658 (C4 (Web Text))

Max Activating Token Index: 221

Text #6

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0659. Min Act: -0.0001

Data Index: 327062 (C4 (Web Text))

Max Activating Token Index: 47

Text #7

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0650. Min Act: -0.0002

Data Index: 407616 (C4 (Web Text))

Max Activating Token Index: 786

Text #8

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0585. Min Act: -0.0001

Data Index: 783894 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0636. Min Act: -0.0001

Data Index: 1220143 (C4 (Web Text))

Max Activating Token Index: 371

Text #10

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0612. Min Act: -0.0001

Data Index: 848849 (C4 (Web Text))

Max Activating Token Index: 614

Text #11

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0654. Min Act: -0.0002

Data Index: 396509 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0600. Min Act: -0.0002

Data Index: 429661 (C4 (Web Text))

Max Activating Token Index: 763

Text #13

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0619. Min Act: -0.0002

Data Index: 756380 (C4 (Web Text))

Max Activating Token Index: 16

Text #14

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0619. Min Act: -0.0002

Data Index: 6561 (C4 (Web Text))

Max Activating Token Index: 16

Text #15

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0597. Min Act: -0.0002

Data Index: 702589 (C4 (Web Text))

Max Activating Token Index: 768

Text #16

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0645. Min Act: -0.0001

Data Index: 48241 (C4 (Web Text))

Max Activating Token Index: 741

Text #17

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1233102 (C4 (Web Text))

Max Activating Token Index: 362

Text #18

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0620. Min Act: -0.0001

Data Index: 882010 (C4 (Web Text))

Max Activating Token Index: 216

Text #19

Max Range: 0.0859. Min Range: -0.0859

Max Act: 0.0504. Min Act: -0.0002

Data Index: 110877 (C4 (Web Text))

Max Activating Token Index: 920