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

Dataset: The Pile

Neuron 2918 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.7374. Min Act: -0.0001

Data Index: 35627 (The Pile)

Max Activating Token Index: 726

Text #1

Max Range: 7.8022. Min Range: -7.8022

Max Act: 7.8022. Min Act: -0.0000

Data Index: 19437 (The Pile)

Max Activating Token Index: 685

Text #2

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.6943. Min Act: -0.0000

Data Index: 1964888 (The Pile)

Max Activating Token Index: 788

Text #3

Max Range: 7.8022. Min Range: -7.8022

Max Act: 7.1513. Min Act: -0.0001

Data Index: 1512755 (The Pile)

Max Activating Token Index: 844

Text #4

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.8206. Min Act: -0.0000

Data Index: 1172116 (The Pile)

Max Activating Token Index: 639

Text #5

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.1120. Min Act: -0.0000

Data Index: 21535 (The Pile)

Max Activating Token Index: 552

Text #6

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.6223. Min Act: -0.0000

Data Index: 408393 (The Pile)

Max Activating Token Index: 813

Text #7

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.8777. Min Act: -0.0000

Data Index: 223545 (The Pile)

Max Activating Token Index: 657

Text #8

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.5713. Min Act: -0.0001

Data Index: 760448 (The Pile)

Max Activating Token Index: 819

Text #9

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.5401. Min Act: -0.0001

Data Index: 1412292 (The Pile)

Max Activating Token Index: 942

Text #10

Max Range: 7.8022. Min Range: -7.8022

Max Act: 5.1990. Min Act: -0.0000

Data Index: 1898722 (The Pile)

Max Activating Token Index: 519

Text #11

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.5176. Min Act: -0.0000

Data Index: 28420 (The Pile)

Max Activating Token Index: 566

Text #12

Max Range: 7.8022. Min Range: -7.8022

Max Act: 5.8483. Min Act: -0.0000

Data Index: 616455 (The Pile)

Max Activating Token Index: 777

Text #13

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.2313. Min Act: -0.0000

Data Index: 1452201 (The Pile)

Max Activating Token Index: 818

Text #14

Max Range: 7.8022. Min Range: -7.8022

Max Act: 5.4657. Min Act: -0.0000

Data Index: 1903839 (The Pile)

Max Activating Token Index: 557

Text #15

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.2420. Min Act: -0.0001

Data Index: 1430583 (The Pile)

Max Activating Token Index: 831

Text #16

Max Range: 7.8022. Min Range: -7.8022

Max Act: 6.1042. Min Act: -0.0000

Data Index: 768972 (The Pile)

Max Activating Token Index: 866

Text #17

Max Range: 7.8022. Min Range: -7.8022

Max Act: 4.9490. Min Act: -0.0000

Data Index: 108228 (The Pile)

Max Activating Token Index: 401

Text #18

Max Range: 7.8022. Min Range: -7.8022

Max Act: 4.9953. Min Act: -0.0000

Data Index: 872311 (The Pile)

Max Activating Token Index: 513

Text #19

Max Range: 7.8022. Min Range: -7.8022

Max Act: 5.3957. Min Act: -0.0001

Data Index: 1022161 (The Pile)

Max Activating Token Index: 681