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

Dataset: The Pile

Neuron 4717 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7979. Min Act: -0.0000

Data Index: 1717010 (The Pile)

Max Activating Token Index: 800

Text #1

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.7906. Min Act: -0.0000

Data Index: 62050 (The Pile)

Max Activating Token Index: 259

Text #2

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6588. Min Act: -0.0000

Data Index: 477860 (The Pile)

Max Activating Token Index: 279

Text #3

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6185. Min Act: -0.0000

Data Index: 1448323 (The Pile)

Max Activating Token Index: 80

Text #4

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5731. Min Act: -0.0000

Data Index: 463750 (The Pile)

Max Activating Token Index: 1020

Text #5

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5993. Min Act: -0.0000

Data Index: 916866 (The Pile)

Max Activating Token Index: 965

Text #6

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.6133. Min Act: -0.0000

Data Index: 930032 (The Pile)

Max Activating Token Index: 980

Text #7

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1517428 (The Pile)

Max Activating Token Index: 486

Text #8

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5762. Min Act: -0.0000

Data Index: 681424 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5427. Min Act: -0.0000

Data Index: 1292113 (The Pile)

Max Activating Token Index: 726

Text #10

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5748. Min Act: -0.0000

Data Index: 549087 (The Pile)

Max Activating Token Index: 722

Text #11

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4942. Min Act: -0.0000

Data Index: 1314075 (The Pile)

Max Activating Token Index: 967

Text #12

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5310. Min Act: -0.0000

Data Index: 1773315 (The Pile)

Max Activating Token Index: 775

Text #13

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5470. Min Act: -0.0000

Data Index: 616588 (The Pile)

Max Activating Token Index: 247

Text #14

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5035. Min Act: -0.0000

Data Index: 673527 (The Pile)

Max Activating Token Index: 903

Text #15

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.5132. Min Act: -0.0000

Data Index: 716296 (The Pile)

Max Activating Token Index: 99

Text #16

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4791. Min Act: -0.0000

Data Index: 566747 (The Pile)

Max Activating Token Index: 887

Text #17

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4453. Min Act: -0.0000

Data Index: 1686326 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4288. Min Act: -0.0000

Data Index: 651949 (The Pile)

Max Activating Token Index: 658

Text #19

Max Range: 0.7979. Min Range: -0.7979

Max Act: 0.4422. Min Act: -0.0000

Data Index: 318463 (The Pile)

Max Activating Token Index: 693