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

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

Neuron 3445 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: 3.2056. Min Range: -3.2056

Max Act: 3.2056. Min Act: -0.0000

Data Index: 582173 (C4 (Web Text))

Max Activating Token Index: 113

Text #1

Max Range: 3.2056. Min Range: -3.2056

Max Act: 3.1263. Min Act: -0.0000

Data Index: 1018112 (C4 (Web Text))

Max Activating Token Index: 91

Text #2

Max Range: 3.2056. Min Range: -3.2056

Max Act: 3.0668. Min Act: -0.0000

Data Index: 202928 (C4 (Web Text))

Max Activating Token Index: 40

Text #3

Max Range: 3.2056. Min Range: -3.2056

Max Act: 3.0338. Min Act: -0.0001

Data Index: 981928 (C4 (Web Text))

Max Activating Token Index: 40

Text #4

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.9792. Min Act: -0.0001

Data Index: 1134794 (C4 (Web Text))

Max Activating Token Index: 91

Text #5

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.7550. Min Act: -0.0000

Data Index: 1144234 (C4 (Web Text))

Max Activating Token Index: 822

Text #6

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.7998. Min Act: -0.0000

Data Index: 1013659 (C4 (Web Text))

Max Activating Token Index: 42

Text #7

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.6504. Min Act: -0.0000

Data Index: 672413 (C4 (Web Text))

Max Activating Token Index: 78

Text #8

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.4441. Min Act: -0.0001

Data Index: 1062413 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.5635. Min Act: -0.0000

Data Index: 929754 (C4 (Web Text))

Max Activating Token Index: 94

Text #10

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.4995. Min Act: -0.0000

Data Index: 549615 (C4 (Web Text))

Max Activating Token Index: 52

Text #11

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.6133. Min Act: -0.0000

Data Index: 837825 (C4 (Web Text))

Max Activating Token Index: 95

Text #12

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.4713. Min Act: -0.0000

Data Index: 24346 (C4 (Web Text))

Max Activating Token Index: 263

Text #13

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.6655. Min Act: -0.0001

Data Index: 261333 (C4 (Web Text))

Max Activating Token Index: 93

Text #14

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.5283. Min Act: -0.0000

Data Index: 949355 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.7077. Min Act: -0.0000

Data Index: 1073038 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.6800. Min Act: -0.0000

Data Index: 509901 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.4576. Min Act: -0.0000

Data Index: 239258 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.4428. Min Act: -0.0001

Data Index: 35164 (C4 (Web Text))

Max Activating Token Index: 56

Text #19

Max Range: 3.2056. Min Range: -3.2056

Max Act: 2.6138. Min Act: -0.0000

Data Index: 670265 (C4 (Web Text))

Max Activating Token Index: 689