Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2204 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7871. Min Act: -0.0001

Data Index: 1499343 (Python Code)

Max Activating Token Index: 796

Text #1

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7903. Min Act: -0.0000

Data Index: 1445100 (Python Code)

Max Activating Token Index: 410

Text #2

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7827. Min Act: -0.0001

Data Index: 1547788 (Python Code)

Max Activating Token Index: 374

Text #3

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1624858 (Python Code)

Max Activating Token Index: 815

Text #4

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7698. Min Act: 0.0000

Data Index: 1530648 (Python Code)

Max Activating Token Index: 959

Text #5

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7480. Min Act: -0.0001

Data Index: 690105 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7184. Min Act: -0.0001

Data Index: 1586380 (Python Code)

Max Activating Token Index: 429

Text #7

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7141. Min Act: -0.0000

Data Index: 1561317 (Python Code)

Max Activating Token Index: 570

Text #8

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6868. Min Act: -0.0001

Data Index: 1446449 (Python Code)

Max Activating Token Index: 172

Text #9

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.7099. Min Act: -0.0000

Data Index: 1625763 (Python Code)

Max Activating Token Index: 760

Text #10

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6773. Min Act: 0.0000

Data Index: 1525515 (Python Code)

Max Activating Token Index: 698

Text #11

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6765. Min Act: -0.0000

Data Index: 549617 (C4 (Web Text))

Max Activating Token Index: 197

Text #12

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6926. Min Act: -0.0000

Data Index: 1440295 (Python Code)

Max Activating Token Index: 944

Text #13

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6507. Min Act: 0.0000

Data Index: 1507041 (Python Code)

Max Activating Token Index: 935

Text #14

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6404. Min Act: -0.0000

Data Index: 925901 (C4 (Web Text))

Max Activating Token Index: 319

Text #15

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6548. Min Act: -0.0000

Data Index: 1553382 (Python Code)

Max Activating Token Index: 235

Text #16

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6189. Min Act: -0.0000

Data Index: 1385745 (Python Code)

Max Activating Token Index: 744

Text #17

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1559297 (Python Code)

Max Activating Token Index: 261

Text #18

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6253. Min Act: 0.0000

Data Index: 1452562 (Python Code)

Max Activating Token Index: 417

Text #19

Max Range: 0.7903. Min Range: -0.7903

Max Act: 0.6255. Min Act: 0.0000

Data Index: 1376143 (Python Code)

Max Activating Token Index: 1011