Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1977 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1124. Min Act: -0.0002

Data Index: 602894 (C4 (Web Text))

Max Activating Token Index: 466

Text #1

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1104. Min Act: -0.0002

Data Index: 562140 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1141. Min Act: -0.0002

Data Index: 691353 (C4 (Web Text))

Max Activating Token Index: 184

Text #3

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1140. Min Act: -0.0002

Data Index: 931051 (C4 (Web Text))

Max Activating Token Index: 462

Text #4

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1118. Min Act: -0.0002

Data Index: 86230 (C4 (Web Text))

Max Activating Token Index: 207

Text #5

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.1069. Min Act: -0.0002

Data Index: 537947 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0987. Min Act: -0.0002

Data Index: 528179 (C4 (Web Text))

Max Activating Token Index: 900

Text #7

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0957. Min Act: -0.0002

Data Index: 1050083 (C4 (Web Text))

Max Activating Token Index: 395

Text #8

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0995. Min Act: -0.0002

Data Index: 290484 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0938. Min Act: -0.0002

Data Index: 1324731 (C4 (Web Text))

Max Activating Token Index: 736

Text #10

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0908. Min Act: -0.0002

Data Index: 1255852 (C4 (Web Text))

Max Activating Token Index: 471

Text #11

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0888. Min Act: -0.0002

Data Index: 441332 (C4 (Web Text))

Max Activating Token Index: 404

Text #12

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0867. Min Act: -0.0002

Data Index: 1100865 (C4 (Web Text))

Max Activating Token Index: 381

Text #13

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0871. Min Act: -0.0002

Data Index: 290224 (C4 (Web Text))

Max Activating Token Index: 367

Text #14

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0864. Min Act: -0.0002

Data Index: 484185 (C4 (Web Text))

Max Activating Token Index: 536

Text #15

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1234527 (C4 (Web Text))

Max Activating Token Index: 190

Text #16

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0820. Min Act: -0.0002

Data Index: 748323 (C4 (Web Text))

Max Activating Token Index: 793

Text #17

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0853. Min Act: -0.0002

Data Index: 1237976 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0843. Min Act: -0.0002

Data Index: 1252414 (C4 (Web Text))

Max Activating Token Index: 543

Text #19

Max Range: 0.1141. Min Range: -0.1141

Max Act: 0.0831. Min Act: -0.0002

Data Index: 992092 (C4 (Web Text))

Max Activating Token Index: 228