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

Dataset: The Pile

Neuron 248 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6798. Min Act: -0.0000

Data Index: 150307 (The Pile)

Max Activating Token Index: 317

Text #1

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.7042. Min Act: -0.0000

Data Index: 576533 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6259. Min Act: -0.0000

Data Index: 865501 (The Pile)

Max Activating Token Index: 292

Text #3

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.7082. Min Act: -0.0000

Data Index: 1758337 (The Pile)

Max Activating Token Index: 241

Text #4

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1967314 (The Pile)

Max Activating Token Index: 420

Text #5

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5900. Min Act: -0.0000

Data Index: 1652620 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6003. Min Act: -0.0000

Data Index: 1900451 (The Pile)

Max Activating Token Index: 190

Text #7

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5472. Min Act: -0.0000

Data Index: 291895 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.6044. Min Act: -0.0000

Data Index: 321873 (The Pile)

Max Activating Token Index: 108

Text #9

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1808547 (The Pile)

Max Activating Token Index: 548

Text #10

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5384. Min Act: -0.0000

Data Index: 1064300 (The Pile)

Max Activating Token Index: 236

Text #11

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5222. Min Act: -0.0000

Data Index: 87288 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4910. Min Act: -0.0000

Data Index: 1857025 (The Pile)

Max Activating Token Index: 331

Text #13

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4892. Min Act: -0.0000

Data Index: 1274946 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.5228. Min Act: -0.0000

Data Index: 1502910 (The Pile)

Max Activating Token Index: 970

Text #15

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4986. Min Act: -0.0000

Data Index: 1970977 (The Pile)

Max Activating Token Index: 409

Text #16

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4830. Min Act: -0.0000

Data Index: 1462162 (The Pile)

Max Activating Token Index: 595

Text #17

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4729. Min Act: -0.0000

Data Index: 213268 (The Pile)

Max Activating Token Index: 170

Text #18

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4880. Min Act: -0.0000

Data Index: 739154 (The Pile)

Max Activating Token Index: 486

Text #19

Max Range: 0.7082. Min Range: -0.7082

Max Act: 0.4565. Min Act: -0.0000

Data Index: 314155 (The Pile)

Max Activating Token Index: 985