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

Dataset: The Pile

Neuron 2349 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: 1.3333. Min Range: -1.3333

Max Act: 1.3000. Min Act: -0.0000

Data Index: 1155352 (The Pile)

Max Activating Token Index: 716

Text #1

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.3333. Min Act: -0.0000

Data Index: 1979382 (The Pile)

Max Activating Token Index: 769

Text #2

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.1727. Min Act: -0.0000

Data Index: 1160108 (The Pile)

Max Activating Token Index: 621

Text #3

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.2150. Min Act: -0.0000

Data Index: 38269 (The Pile)

Max Activating Token Index: 645

Text #4

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.1240. Min Act: -0.0000

Data Index: 1322853 (The Pile)

Max Activating Token Index: 266

Text #5

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0983. Min Act: -0.0000

Data Index: 628246 (The Pile)

Max Activating Token Index: 244

Text #6

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1004911 (The Pile)

Max Activating Token Index: 848

Text #7

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1297481 (The Pile)

Max Activating Token Index: 987

Text #8

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.1122. Min Act: -0.0000

Data Index: 516718 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.1094. Min Act: -0.0000

Data Index: 1715358 (The Pile)

Max Activating Token Index: 214

Text #10

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0806. Min Act: -0.0000

Data Index: 786509 (The Pile)

Max Activating Token Index: 516

Text #11

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.9795. Min Act: -0.0000

Data Index: 1835348 (The Pile)

Max Activating Token Index: 838

Text #12

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0109. Min Act: -0.0000

Data Index: 1509045 (The Pile)

Max Activating Token Index: 538

Text #13

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1162714 (The Pile)

Max Activating Token Index: 53

Text #14

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0188. Min Act: -0.0000

Data Index: 485473 (The Pile)

Max Activating Token Index: 550

Text #15

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.9942. Min Act: -0.0000

Data Index: 1083489 (The Pile)

Max Activating Token Index: 387

Text #16

Max Range: 1.3333. Min Range: -1.3333

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1779091 (The Pile)

Max Activating Token Index: 641

Text #17

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.9712. Min Act: -0.0000

Data Index: 1916384 (The Pile)

Max Activating Token Index: 526

Text #18

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1961284 (The Pile)

Max Activating Token Index: 762

Text #19

Max Range: 1.3333. Min Range: -1.3333

Max Act: 0.9878. Min Act: -0.0000

Data Index: 1620080 (The Pile)

Max Activating Token Index: 920