Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1217 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7529. Min Act: -0.0000

Data Index: 1086814 (The Pile)

Max Activating Token Index: 780

Text #1

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7548. Min Act: -0.0000

Data Index: 35353 (The Pile)

Max Activating Token Index: 510

Text #2

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1884792 (The Pile)

Max Activating Token Index: 798

Text #3

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.7068. Min Act: -0.0000

Data Index: 1741396 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6997. Min Act: -0.0000

Data Index: 354619 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6818. Min Act: -0.0000

Data Index: 387038 (The Pile)

Max Activating Token Index: 663

Text #6

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6777. Min Act: -0.0000

Data Index: 2284 (The Pile)

Max Activating Token Index: 114

Text #7

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6641. Min Act: -0.0000

Data Index: 1145109 (The Pile)

Max Activating Token Index: 830

Text #8

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6740. Min Act: -0.0000

Data Index: 1931292 (The Pile)

Max Activating Token Index: 942

Text #9

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6315. Min Act: -0.0000

Data Index: 405787 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6492. Min Act: -0.0000

Data Index: 1600818 (The Pile)

Max Activating Token Index: 396

Text #11

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6245. Min Act: -0.0000

Data Index: 1644658 (The Pile)

Max Activating Token Index: 964

Text #12

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6229. Min Act: -0.0000

Data Index: 1065015 (The Pile)

Max Activating Token Index: 161

Text #13

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1418180 (The Pile)

Max Activating Token Index: 43

Text #14

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6186. Min Act: -0.0000

Data Index: 1706197 (The Pile)

Max Activating Token Index: 335

Text #15

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6175. Min Act: -0.0000

Data Index: 631647 (The Pile)

Max Activating Token Index: 205

Text #16

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1660822 (The Pile)

Max Activating Token Index: 159

Text #17

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6331. Min Act: -0.0000

Data Index: 185956 (The Pile)

Max Activating Token Index: 340

Text #18

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6486. Min Act: -0.0000

Data Index: 1244668 (The Pile)

Max Activating Token Index: 554

Text #19

Max Range: 0.7548. Min Range: -0.7548

Max Act: 0.6243. Min Act: -0.0000

Data Index: 1076523 (The Pile)

Max Activating Token Index: 149