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

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

Neuron 196 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: 2.7103. Min Range: -2.7103

Max Act: 2.7103. Min Act: -0.0000

Data Index: 1461554 (Python Code)

Max Activating Token Index: 316

Text #1

Max Range: 2.7103. Min Range: -2.7103

Max Act: 2.2031. Min Act: -0.0000

Data Index: 407093 (C4 (Web Text))

Max Activating Token Index: 81

Text #2

Max Range: 2.7103. Min Range: -2.7103

Max Act: 2.0619. Min Act: -0.0000

Data Index: 1404914 (Python Code)

Max Activating Token Index: 52

Text #3

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.9082. Min Act: -0.0000

Data Index: 1373441 (Python Code)

Max Activating Token Index: 502

Text #4

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.9146. Min Act: -0.0000

Data Index: 1590412 (Python Code)

Max Activating Token Index: 881

Text #5

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.7341. Min Act: -0.0000

Data Index: 1628813 (Python Code)

Max Activating Token Index: 330

Text #6

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.8486. Min Act: -0.0000

Data Index: 1619491 (Python Code)

Max Activating Token Index: 153

Text #7

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.8363. Min Act: -0.0000

Data Index: 1530633 (Python Code)

Max Activating Token Index: 452

Text #8

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.7017. Min Act: -0.0000

Data Index: 1553896 (Python Code)

Max Activating Token Index: 819

Text #9

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.7555. Min Act: -0.0000

Data Index: 691451 (C4 (Web Text))

Max Activating Token Index: 17

Text #10

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.7417. Min Act: -0.0000

Data Index: 1404324 (Python Code)

Max Activating Token Index: 301

Text #11

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.7565. Min Act: -0.0000

Data Index: 369792 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.6271. Min Act: -0.0000

Data Index: 1546090 (Python Code)

Max Activating Token Index: 387

Text #13

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.7161. Min Act: -0.0000

Data Index: 1616061 (Python Code)

Max Activating Token Index: 616

Text #14

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.6798. Min Act: -0.0000

Data Index: 1347986 (C4 (Web Text))

Max Activating Token Index: 448

Text #15

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.5771. Min Act: -0.0000

Data Index: 1419570 (Python Code)

Max Activating Token Index: 924

Text #16

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.5865. Min Act: -0.0000

Data Index: 1556943 (Python Code)

Max Activating Token Index: 478

Text #17

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.6629. Min Act: -0.0000

Data Index: 162871 (C4 (Web Text))

Max Activating Token Index: 158

Text #18

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.7765. Min Act: -0.0000

Data Index: 1367919 (Python Code)

Max Activating Token Index: 466

Text #19

Max Range: 2.7103. Min Range: -2.7103

Max Act: 1.4902. Min Act: -0.0000

Data Index: 322481 (C4 (Web Text))

Max Activating Token Index: 919