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

Dataset: The Pile

Neuron 332 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: 3.2477. Min Range: -3.2477

Max Act: 2.9629. Min Act: -0.0000

Data Index: 1234141 (The Pile)

Max Activating Token Index: 250

Text #1

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.1055. Min Act: -0.0000

Data Index: 669685 (The Pile)

Max Activating Token Index: 636

Text #2

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.0859. Min Act: -0.0000

Data Index: 1687097 (The Pile)

Max Activating Token Index: 641

Text #3

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.1010. Min Act: -0.0000

Data Index: 1147045 (The Pile)

Max Activating Token Index: 600

Text #4

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.0786. Min Act: -0.0000

Data Index: 1160182 (The Pile)

Max Activating Token Index: 462

Text #5

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.0642. Min Act: -0.0000

Data Index: 937092 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.0742. Min Act: -0.0000

Data Index: 1703820 (The Pile)

Max Activating Token Index: 302

Text #7

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.1342. Min Act: -0.0000

Data Index: 1563401 (The Pile)

Max Activating Token Index: 334

Text #8

Max Range: 3.2477. Min Range: -3.2477

Max Act: 2.8465. Min Act: -0.0000

Data Index: 1023289 (The Pile)

Max Activating Token Index: 837

Text #9

Max Range: 3.2477. Min Range: -3.2477

Max Act: 2.9574. Min Act: -0.0000

Data Index: 1770405 (The Pile)

Max Activating Token Index: 645

Text #10

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.1067. Min Act: -0.0000

Data Index: 883591 (The Pile)

Max Activating Token Index: 680

Text #11

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.1044. Min Act: -0.0000

Data Index: 1282551 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.0972. Min Act: -0.0000

Data Index: 1104984 (The Pile)

Max Activating Token Index: 460

Text #13

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.1021. Min Act: -0.0000

Data Index: 364843 (The Pile)

Max Activating Token Index: 454

Text #14

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.0985. Min Act: -0.0000

Data Index: 251514 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.2477. Min Act: -0.0000

Data Index: 32739 (The Pile)

Max Activating Token Index: 550

Text #16

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.0956. Min Act: -0.0000

Data Index: 1768350 (The Pile)

Max Activating Token Index: 796

Text #17

Max Range: 3.2477. Min Range: -3.2477

Max Act: 2.9622. Min Act: -0.0000

Data Index: 844648 (The Pile)

Max Activating Token Index: 747

Text #18

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.0871. Min Act: -0.0000

Data Index: 71987 (The Pile)

Max Activating Token Index: 359

Text #19

Max Range: 3.2477. Min Range: -3.2477

Max Act: 3.2278. Min Act: -0.0000

Data Index: 1353654 (The Pile)

Max Activating Token Index: 707