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

Dataset: The Pile

Neuron 3331 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: 3.0331. Min Range: -3.0331

Max Act: 3.0331. Min Act: -0.0000

Data Index: 1235142 (The Pile)

Max Activating Token Index: 231

Text #1

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.7626. Min Act: -0.0000

Data Index: 1051113 (The Pile)

Max Activating Token Index: 38

Text #2

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.8143. Min Act: -0.0000

Data Index: 372157 (The Pile)

Max Activating Token Index: 455

Text #3

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.9223. Min Act: -0.0000

Data Index: 1308349 (The Pile)

Max Activating Token Index: 386

Text #4

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.7600. Min Act: -0.0000

Data Index: 127070 (The Pile)

Max Activating Token Index: 220

Text #5

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.6867. Min Act: -0.0000

Data Index: 1837334 (The Pile)

Max Activating Token Index: 182

Text #6

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.6703. Min Act: -0.0000

Data Index: 1477806 (The Pile)

Max Activating Token Index: 776

Text #7

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.6454. Min Act: -0.0000

Data Index: 1965295 (The Pile)

Max Activating Token Index: 450

Text #8

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.5973. Min Act: -0.0000

Data Index: 768288 (The Pile)

Max Activating Token Index: 578

Text #9

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.5990. Min Act: -0.0000

Data Index: 172342 (The Pile)

Max Activating Token Index: 777

Text #10

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.5910. Min Act: -0.0000

Data Index: 262838 (The Pile)

Max Activating Token Index: 305

Text #11

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.3111. Min Act: -0.0000

Data Index: 527465 (The Pile)

Max Activating Token Index: 952

Text #12

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.5875. Min Act: -0.0000

Data Index: 650270 (The Pile)

Max Activating Token Index: 295

Text #13

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.5737. Min Act: -0.0000

Data Index: 100298 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.6719. Min Act: -0.0000

Data Index: 595995 (The Pile)

Max Activating Token Index: 341

Text #15

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.4129. Min Act: -0.0000

Data Index: 632724 (The Pile)

Max Activating Token Index: 636

Text #16

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.5295. Min Act: -0.0000

Data Index: 818413 (The Pile)

Max Activating Token Index: 220

Text #17

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.5066. Min Act: -0.0000

Data Index: 1812584 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.3876. Min Act: -0.0000

Data Index: 516038 (The Pile)

Max Activating Token Index: 87

Text #19

Max Range: 3.0331. Min Range: -3.0331

Max Act: 2.5041. Min Act: -0.0000

Data Index: 1675192 (The Pile)

Max Activating Token Index: 840