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

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

Neuron 911 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.5863. Min Act: -0.0000

Data Index: 194563 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.6074. Min Act: -0.0000

Data Index: 69707 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.6866. Min Act: -0.0000

Data Index: 906653 (C4 (Web Text))

Max Activating Token Index: 568

Text #3

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.5537. Min Act: -0.0000

Data Index: 1601818 (Python Code)

Max Activating Token Index: 392

Text #4

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4254. Min Act: -0.0000

Data Index: 1390327 (Python Code)

Max Activating Token Index: 977

Text #5

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4814. Min Act: -0.0000

Data Index: 1433759 (Python Code)

Max Activating Token Index: 585

Text #6

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4692. Min Act: -0.0000

Data Index: 975121 (C4 (Web Text))

Max Activating Token Index: 551

Text #7

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4221. Min Act: -0.0000

Data Index: 1637799 (Python Code)

Max Activating Token Index: 483

Text #8

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4154. Min Act: -0.0000

Data Index: 485423 (C4 (Web Text))

Max Activating Token Index: 460

Text #9

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4119. Min Act: -0.0000

Data Index: 1586020 (Python Code)

Max Activating Token Index: 495

Text #10

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.4469. Min Act: -0.0000

Data Index: 181405 (C4 (Web Text))

Max Activating Token Index: 781

Text #11

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.3417. Min Act: -0.0000

Data Index: 99239 (C4 (Web Text))

Max Activating Token Index: 827

Text #12

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2916. Min Act: -0.0000

Data Index: 1466741 (Python Code)

Max Activating Token Index: 610

Text #13

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.3374. Min Act: -0.0000

Data Index: 1633107 (Python Code)

Max Activating Token Index: 250

Text #14

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2914. Min Act: -0.0000

Data Index: 462084 (C4 (Web Text))

Max Activating Token Index: 95

Text #15

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1553821 (Python Code)

Max Activating Token Index: 819

Text #16

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2762. Min Act: -0.0000

Data Index: 251427 (C4 (Web Text))

Max Activating Token Index: 620

Text #17

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2722. Min Act: -0.0000

Data Index: 1425229 (Python Code)

Max Activating Token Index: 192

Text #18

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2577. Min Act: -0.0000

Data Index: 809740 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 1.6866. Min Range: -1.6866

Max Act: 1.2539. Min Act: -0.0000

Data Index: 1285275 (C4 (Web Text))

Max Activating Token Index: 236