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

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

Neuron 1944 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: 2.1940. Min Range: -2.1940

Max Act: 2.1940. Min Act: -0.0000

Data Index: 469265 (C4 (Web Text))

Max Activating Token Index: 618

Text #1

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.9581. Min Act: -0.0000

Data Index: 198959 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 2.1940. Min Range: -2.1940

Max Act: 1.0134. Min Act: -0.0000

Data Index: 1081860 (C4 (Web Text))

Max Activating Token Index: 607

Text #3

Max Range: 2.1940. Min Range: -2.1940

Max Act: 1.0039. Min Act: -0.0000

Data Index: 39648 (C4 (Web Text))

Max Activating Token Index: 796

Text #4

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8289. Min Act: 0.0000

Data Index: 416318 (C4 (Web Text))

Max Activating Token Index: 696

Text #5

Max Range: 2.1940. Min Range: -2.1940

Max Act: 1.0189. Min Act: -0.0000

Data Index: 1385427 (Python Code)

Max Activating Token Index: 305

Text #6

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.9430. Min Act: -0.0000

Data Index: 145995 (C4 (Web Text))

Max Activating Token Index: 361

Text #7

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.9910. Min Act: -0.0000

Data Index: 1420974 (Python Code)

Max Activating Token Index: 1021

Text #8

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.9646. Min Act: 0.0000

Data Index: 1086388 (C4 (Web Text))

Max Activating Token Index: 942

Text #9

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8766. Min Act: -0.0000

Data Index: 1632828 (Python Code)

Max Activating Token Index: 279

Text #10

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8747. Min Act: -0.0000

Data Index: 1532140 (Python Code)

Max Activating Token Index: 248

Text #11

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8849. Min Act: -0.0000

Data Index: 1372523 (Python Code)

Max Activating Token Index: 273

Text #12

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8719. Min Act: -0.0000

Data Index: 928235 (C4 (Web Text))

Max Activating Token Index: 341

Text #13

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.7925. Min Act: -0.0000

Data Index: 1510409 (Python Code)

Max Activating Token Index: 839

Text #14

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8894. Min Act: -0.0000

Data Index: 818944 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8930. Min Act: -0.0000

Data Index: 400166 (C4 (Web Text))

Max Activating Token Index: 506

Text #16

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8065. Min Act: -0.0000

Data Index: 360483 (C4 (Web Text))

Max Activating Token Index: 730

Text #17

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8571. Min Act: -0.0000

Data Index: 1259869 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8782. Min Act: -0.0000

Data Index: 799879 (C4 (Web Text))

Max Activating Token Index: 446

Text #19

Max Range: 2.1940. Min Range: -2.1940

Max Act: 0.8411. Min Act: -0.0000

Data Index: 1301353 (C4 (Web Text))

Max Activating Token Index: 529