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

Dataset: The Pile

Neuron 1387 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5499. Min Act: 0.0000

Data Index: 1854343 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5739. Min Act: -0.0000

Data Index: 475973 (The Pile)

Max Activating Token Index: 818

Text #2

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5215. Min Act: -0.0000

Data Index: 537212 (The Pile)

Max Activating Token Index: 57

Text #3

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4465. Min Act: -0.0000

Data Index: 1407310 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4907. Min Act: -0.0000

Data Index: 1349441 (The Pile)

Max Activating Token Index: 101

Text #5

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5094. Min Act: 0.0000

Data Index: 1838077 (The Pile)

Max Activating Token Index: 587

Text #6

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4873. Min Act: -0.0000

Data Index: 970939 (The Pile)

Max Activating Token Index: 510

Text #7

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5119. Min Act: -0.0000

Data Index: 1356603 (The Pile)

Max Activating Token Index: 538

Text #8

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4749. Min Act: -0.0000

Data Index: 1118136 (The Pile)

Max Activating Token Index: 598

Text #9

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5362. Min Act: -0.0000

Data Index: 1096206 (The Pile)

Max Activating Token Index: 618

Text #10

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1977934 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.3927. Min Act: -0.0000

Data Index: 1020362 (The Pile)

Max Activating Token Index: 72

Text #12

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5403. Min Act: -0.0000

Data Index: 581145 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4209. Min Act: -0.0000

Data Index: 1918470 (The Pile)

Max Activating Token Index: 137

Text #14

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4015. Min Act: -0.0000

Data Index: 612912 (The Pile)

Max Activating Token Index: 74

Text #15

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.5541. Min Act: -0.0000

Data Index: 841663 (The Pile)

Max Activating Token Index: 202

Text #16

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4314. Min Act: -0.0000

Data Index: 1211791 (The Pile)

Max Activating Token Index: 895

Text #17

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4405. Min Act: -0.0000

Data Index: 1059786 (The Pile)

Max Activating Token Index: 777

Text #18

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4233. Min Act: -0.0000

Data Index: 1322877 (The Pile)

Max Activating Token Index: 135

Text #19

Max Range: 0.5739. Min Range: -0.5739

Max Act: 0.4391. Min Act: 0.0000

Data Index: 1970039 (The Pile)

Max Activating Token Index: 440