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

Dataset: The Pile

Neuron 2433 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: 0.7062. Min Range: -0.7062

Max Act: 0.7062. Min Act: -0.0000

Data Index: 1442560 (The Pile)

Max Activating Token Index: 1011

Text #1

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.6289. Min Act: -0.0000

Data Index: 1224179 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.6467. Min Act: -0.0000

Data Index: 586199 (The Pile)

Max Activating Token Index: 965

Text #3

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.6580. Min Act: -0.0000

Data Index: 722768 (The Pile)

Max Activating Token Index: 699

Text #4

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.6413. Min Act: -0.0000

Data Index: 298498 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1480189 (The Pile)

Max Activating Token Index: 907

Text #6

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5629. Min Act: -0.0000

Data Index: 2869 (The Pile)

Max Activating Token Index: 355

Text #7

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5544. Min Act: -0.0000

Data Index: 1400212 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5670. Min Act: -0.0000

Data Index: 482705 (The Pile)

Max Activating Token Index: 78

Text #9

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5469. Min Act: 0.0001

Data Index: 878305 (The Pile)

Max Activating Token Index: 523

Text #10

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5500. Min Act: -0.0000

Data Index: 1052362 (The Pile)

Max Activating Token Index: 779

Text #11

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1897701 (The Pile)

Max Activating Token Index: 188

Text #12

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5170. Min Act: -0.0000

Data Index: 637840 (The Pile)

Max Activating Token Index: 1023

Text #13

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4928. Min Act: -0.0000

Data Index: 9592 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5055. Min Act: -0.0000

Data Index: 1983602 (The Pile)

Max Activating Token Index: 324

Text #15

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5009. Min Act: -0.0000

Data Index: 1051181 (The Pile)

Max Activating Token Index: 122

Text #16

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5134. Min Act: -0.0000

Data Index: 126786 (The Pile)

Max Activating Token Index: 733

Text #17

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.5142. Min Act: -0.0000

Data Index: 1925837 (The Pile)

Max Activating Token Index: 191

Text #18

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1199355 (The Pile)

Max Activating Token Index: 507

Text #19

Max Range: 0.7062. Min Range: -0.7062

Max Act: 0.4913. Min Act: -0.0000

Data Index: 461316 (The Pile)

Max Activating Token Index: 413