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

Dataset: The Pile

Neuron 2355 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.1105. Min Act: -0.0000

Data Index: 154128 (The Pile)

Max Activating Token Index: 763

Text #1

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.2011. Min Act: -0.0000

Data Index: 176694 (The Pile)

Max Activating Token Index: 100

Text #2

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.0118. Min Act: -0.0000

Data Index: 446109 (The Pile)

Max Activating Token Index: 135

Text #3

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.7363. Min Act: -0.0000

Data Index: 666757 (The Pile)

Max Activating Token Index: 913

Text #4

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9771. Min Act: -0.0000

Data Index: 1549702 (The Pile)

Max Activating Token Index: 826

Text #5

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.3272. Min Act: -0.0000

Data Index: 863673 (The Pile)

Max Activating Token Index: 964

Text #6

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.0108. Min Act: -0.0000

Data Index: 1792337 (The Pile)

Max Activating Token Index: 669

Text #7

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.1083. Min Act: -0.0000

Data Index: 1958581 (The Pile)

Max Activating Token Index: 981

Text #8

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9170. Min Act: -0.0000

Data Index: 1847414 (The Pile)

Max Activating Token Index: 532

Text #9

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.7570. Min Act: -0.0000

Data Index: 191106 (The Pile)

Max Activating Token Index: 329

Text #10

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9885. Min Act: -0.0000

Data Index: 87016 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.8377. Min Act: -0.0000

Data Index: 1085169 (The Pile)

Max Activating Token Index: 200

Text #12

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.8096. Min Act: -0.0000

Data Index: 873132 (The Pile)

Max Activating Token Index: 872

Text #13

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.9806. Min Act: -0.0000

Data Index: 851549 (The Pile)

Max Activating Token Index: 359

Text #14

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.8183. Min Act: -0.0000

Data Index: 1766545 (The Pile)

Max Activating Token Index: 32

Text #15

Max Range: 3.3272. Min Range: -3.3272

Max Act: 3.0574. Min Act: -0.0000

Data Index: 1703872 (The Pile)

Max Activating Token Index: 147

Text #16

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.6594. Min Act: -0.0000

Data Index: 1120615 (The Pile)

Max Activating Token Index: 821

Text #17

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.7315. Min Act: -0.0000

Data Index: 532948 (The Pile)

Max Activating Token Index: 935

Text #18

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.7378. Min Act: -0.0000

Data Index: 1105043 (The Pile)

Max Activating Token Index: 8

Text #19

Max Range: 3.3272. Min Range: -3.3272

Max Act: 2.6127. Min Act: -0.0000

Data Index: 320264 (The Pile)

Max Activating Token Index: 92