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

Dataset: The Pile

Neuron 4926 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.8614. Min Act: -0.0000

Data Index: 1487718 (The Pile)

Max Activating Token Index: 681

Text #1

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.7889. Min Act: -0.0000

Data Index: 1058379 (The Pile)

Max Activating Token Index: 807

Text #2

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6598. Min Act: -0.0000

Data Index: 1828433 (The Pile)

Max Activating Token Index: 459

Text #3

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6086. Min Act: -0.0000

Data Index: 1101903 (The Pile)

Max Activating Token Index: 137

Text #4

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1363444 (The Pile)

Max Activating Token Index: 804

Text #5

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.6200. Min Act: -0.0000

Data Index: 385859 (The Pile)

Max Activating Token Index: 727

Text #6

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5818. Min Act: -0.0000

Data Index: 713945 (The Pile)

Max Activating Token Index: 414

Text #7

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5600. Min Act: -0.0000

Data Index: 1169424 (The Pile)

Max Activating Token Index: 876

Text #8

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5113. Min Act: -0.0000

Data Index: 1958644 (The Pile)

Max Activating Token Index: 975

Text #9

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1114130 (The Pile)

Max Activating Token Index: 386

Text #10

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5300. Min Act: -0.0000

Data Index: 30180 (The Pile)

Max Activating Token Index: 132

Text #11

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1149529 (The Pile)

Max Activating Token Index: 786

Text #12

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5458. Min Act: -0.0000

Data Index: 186941 (The Pile)

Max Activating Token Index: 1009

Text #13

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5090. Min Act: -0.0000

Data Index: 976641 (The Pile)

Max Activating Token Index: 98

Text #14

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5088. Min Act: 0.0001

Data Index: 143879 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.5046. Min Act: -0.0000

Data Index: 851337 (The Pile)

Max Activating Token Index: 61

Text #16

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.4967. Min Act: 0.0000

Data Index: 1082668 (The Pile)

Max Activating Token Index: 44

Text #17

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.4815. Min Act: -0.0000

Data Index: 1736493 (The Pile)

Max Activating Token Index: 698

Text #18

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.4872. Min Act: -0.0000

Data Index: 1243262 (The Pile)

Max Activating Token Index: 796

Text #19

Max Range: 0.8614. Min Range: -0.8614

Max Act: 0.4796. Min Act: 0.0000

Data Index: 1495465 (The Pile)

Max Activating Token Index: 990