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

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

Neuron 3306 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.8161. Min Act: -0.0000

Data Index: 967618 (C4 (Web Text))

Max Activating Token Index: 263

Text #1

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.7519. Min Act: -0.0000

Data Index: 919522 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.7391. Min Act: -0.0000

Data Index: 1174526 (C4 (Web Text))

Max Activating Token Index: 359

Text #3

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.7194. Min Act: -0.0000

Data Index: 75359 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6797. Min Act: -0.0000

Data Index: 504412 (C4 (Web Text))

Max Activating Token Index: 465

Text #5

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6908. Min Act: -0.0000

Data Index: 965227 (C4 (Web Text))

Max Activating Token Index: 1009

Text #6

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6650. Min Act: -0.0000

Data Index: 170122 (C4 (Web Text))

Max Activating Token Index: 564

Text #7

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6558. Min Act: -0.0000

Data Index: 326633 (C4 (Web Text))

Max Activating Token Index: 908

Text #8

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6500. Min Act: -0.0000

Data Index: 161292 (C4 (Web Text))

Max Activating Token Index: 63

Text #9

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6429. Min Act: -0.0000

Data Index: 526842 (C4 (Web Text))

Max Activating Token Index: 386

Text #10

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6331. Min Act: -0.0000

Data Index: 54904 (C4 (Web Text))

Max Activating Token Index: 75

Text #11

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6166. Min Act: -0.0000

Data Index: 768850 (C4 (Web Text))

Max Activating Token Index: 762

Text #12

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6238. Min Act: -0.0000

Data Index: 846638 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6001. Min Act: -0.0000

Data Index: 667699 (C4 (Web Text))

Max Activating Token Index: 663

Text #14

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6190. Min Act: -0.0000

Data Index: 102519 (C4 (Web Text))

Max Activating Token Index: 944

Text #15

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1150384 (C4 (Web Text))

Max Activating Token Index: 294

Text #16

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.6040. Min Act: -0.0000

Data Index: 668622 (C4 (Web Text))

Max Activating Token Index: 372

Text #17

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5969. Min Act: -0.0000

Data Index: 656776 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5860. Min Act: -0.0000

Data Index: 899720 (C4 (Web Text))

Max Activating Token Index: 1006

Text #19

Max Range: 0.8161. Min Range: -0.8161

Max Act: 0.5843. Min Act: -0.0000

Data Index: 223480 (C4 (Web Text))

Max Activating Token Index: 343