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

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

Neuron 6097 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: 4.8789. Min Range: -4.8789

Max Act: 4.8196. Min Act: -0.0000

Data Index: 1047634 (C4 (Web Text))

Max Activating Token Index: 492

Text #1

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.7057. Min Act: -0.0000

Data Index: 697025 (C4 (Web Text))

Max Activating Token Index: 479

Text #2

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.7030. Min Act: -0.0000

Data Index: 99125 (C4 (Web Text))

Max Activating Token Index: 450

Text #3

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.8789. Min Act: -0.0000

Data Index: 815773 (C4 (Web Text))

Max Activating Token Index: 531

Text #4

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.3681. Min Act: -0.0000

Data Index: 388377 (C4 (Web Text))

Max Activating Token Index: 369

Text #5

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.5346. Min Act: -0.0000

Data Index: 1113028 (C4 (Web Text))

Max Activating Token Index: 423

Text #6

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.5030. Min Act: -0.0000

Data Index: 446216 (C4 (Web Text))

Max Activating Token Index: 895

Text #7

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.4239. Min Act: -0.0000

Data Index: 410551 (C4 (Web Text))

Max Activating Token Index: 169

Text #8

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.2306. Min Act: -0.0000

Data Index: 78255 (C4 (Web Text))

Max Activating Token Index: 370

Text #9

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.4033. Min Act: -0.0000

Data Index: 1486889 (Python Code)

Max Activating Token Index: 762

Text #10

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.5380. Min Act: -0.0000

Data Index: 332665 (C4 (Web Text))

Max Activating Token Index: 484

Text #11

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.3151. Min Act: -0.0000

Data Index: 1338941 (C4 (Web Text))

Max Activating Token Index: 584

Text #12

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.0076. Min Act: -0.0000

Data Index: 509989 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.1561. Min Act: -0.0000

Data Index: 583078 (C4 (Web Text))

Max Activating Token Index: 377

Text #14

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.1619. Min Act: -0.0000

Data Index: 795251 (C4 (Web Text))

Max Activating Token Index: 564

Text #15

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.3028. Min Act: -0.0000

Data Index: 877957 (C4 (Web Text))

Max Activating Token Index: 310

Text #16

Max Range: 4.8789. Min Range: -4.8789

Max Act: 3.9205. Min Act: -0.0000

Data Index: 592931 (C4 (Web Text))

Max Activating Token Index: 918

Text #17

Max Range: 4.8789. Min Range: -4.8789

Max Act: 3.8254. Min Act: -0.0000

Data Index: 678730 (C4 (Web Text))

Max Activating Token Index: 504

Text #18

Max Range: 4.8789. Min Range: -4.8789

Max Act: 4.3566. Min Act: -0.0000

Data Index: 489597 (C4 (Web Text))

Max Activating Token Index: 294

Text #19

Max Range: 4.8789. Min Range: -4.8789

Max Act: 3.7933. Min Act: -0.0000

Data Index: 5625 (C4 (Web Text))

Max Activating Token Index: 701