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

Dataset: The Pile

Neuron 3177 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3975. Min Act: -0.0000

Data Index: 1764863 (The Pile)

Max Activating Token Index: 593

Text #1

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3975. Min Act: -0.0000

Data Index: 996439 (The Pile)

Max Activating Token Index: 144

Text #2

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3691. Min Act: -0.0000

Data Index: 375207 (The Pile)

Max Activating Token Index: 464

Text #3

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3746. Min Act: -0.0000

Data Index: 1146958 (The Pile)

Max Activating Token Index: 450

Text #4

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3358. Min Act: -0.0000

Data Index: 1265232 (The Pile)

Max Activating Token Index: 209

Text #5

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3011. Min Act: -0.0000

Data Index: 940350 (The Pile)

Max Activating Token Index: 305

Text #6

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1750236 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3317. Min Act: -0.0000

Data Index: 1837379 (The Pile)

Max Activating Token Index: 685

Text #8

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3126. Min Act: -0.0000

Data Index: 1583795 (The Pile)

Max Activating Token Index: 205

Text #9

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2916. Min Act: -0.0000

Data Index: 1823798 (The Pile)

Max Activating Token Index: 441

Text #10

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3326. Min Act: -0.0000

Data Index: 211258 (The Pile)

Max Activating Token Index: 419

Text #11

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3308. Min Act: -0.0000

Data Index: 220268 (The Pile)

Max Activating Token Index: 765

Text #12

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2854. Min Act: -0.0000

Data Index: 110496 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2929. Min Act: -0.0000

Data Index: 163590 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3045. Min Act: -0.0000

Data Index: 1210139 (The Pile)

Max Activating Token Index: 983

Text #15

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.3023. Min Act: -0.0000

Data Index: 153954 (The Pile)

Max Activating Token Index: 271

Text #16

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2595. Min Act: -0.0000

Data Index: 1239379 (The Pile)

Max Activating Token Index: 501

Text #17

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2756. Min Act: -0.0000

Data Index: 1258798 (The Pile)

Max Activating Token Index: 96

Text #18

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2754. Min Act: -0.0000

Data Index: 1187665 (The Pile)

Max Activating Token Index: 584

Text #19

Max Range: 0.3975. Min Range: -0.3975

Max Act: 0.2825. Min Act: -0.0000

Data Index: 1961105 (The Pile)

Max Activating Token Index: 625