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

Dataset: The Pile

Neuron 1667 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: 1.0466. Min Range: -1.0466

Max Act: 1.0466. Min Act: -0.0000

Data Index: 466865 (The Pile)

Max Activating Token Index: 425

Text #1

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.9697. Min Act: -0.0000

Data Index: 1260780 (The Pile)

Max Activating Token Index: 196

Text #2

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.9602. Min Act: -0.0000

Data Index: 449948 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8533. Min Act: -0.0000

Data Index: 1964437 (The Pile)

Max Activating Token Index: 935

Text #4

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.8965. Min Act: -0.0000

Data Index: 466678 (The Pile)

Max Activating Token Index: 647

Text #5

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7561. Min Act: -0.0000

Data Index: 1181929 (The Pile)

Max Activating Token Index: 446

Text #6

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7202. Min Act: -0.0000

Data Index: 449757 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7523. Min Act: -0.0000

Data Index: 1130704 (The Pile)

Max Activating Token Index: 183

Text #8

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1997999 (The Pile)

Max Activating Token Index: 172

Text #9

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1046087 (The Pile)

Max Activating Token Index: 848

Text #10

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6394. Min Act: -0.0000

Data Index: 1135939 (The Pile)

Max Activating Token Index: 444

Text #11

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6044. Min Act: -0.0000

Data Index: 863168 (The Pile)

Max Activating Token Index: 582

Text #12

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6712. Min Act: -0.0000

Data Index: 783091 (The Pile)

Max Activating Token Index: 955

Text #13

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6467. Min Act: -0.0000

Data Index: 354337 (The Pile)

Max Activating Token Index: 811

Text #14

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6673. Min Act: -0.0000

Data Index: 1436128 (The Pile)

Max Activating Token Index: 514

Text #15

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6129. Min Act: -0.0000

Data Index: 95723 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6321. Min Act: -0.0000

Data Index: 1224182 (The Pile)

Max Activating Token Index: 199

Text #17

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.5869. Min Act: -0.0000

Data Index: 1782060 (The Pile)

Max Activating Token Index: 862

Text #18

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6094. Min Act: -0.0000

Data Index: 1793669 (The Pile)

Max Activating Token Index: 358

Text #19

Max Range: 1.0466. Min Range: -1.0466

Max Act: 0.6271. Min Act: -0.0000

Data Index: 1437698 (The Pile)

Max Activating Token Index: 370