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

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

Neuron 2134 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: 0.7803. Min Range: -0.7803

Max Act: 0.7803. Min Act: -0.0000

Data Index: 108488 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7256. Min Act: -0.0000

Data Index: 827146 (C4 (Web Text))

Max Activating Token Index: 402

Text #2

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.7061. Min Act: -0.0000

Data Index: 1064792 (C4 (Web Text))

Max Activating Token Index: 477

Text #3

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6853. Min Act: -0.0001

Data Index: 702522 (C4 (Web Text))

Max Activating Token Index: 887

Text #4

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6380. Min Act: -0.0000

Data Index: 341505 (C4 (Web Text))

Max Activating Token Index: 223

Text #5

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5965. Min Act: -0.0000

Data Index: 919157 (C4 (Web Text))

Max Activating Token Index: 628

Text #6

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6220. Min Act: -0.0000

Data Index: 1176604 (C4 (Web Text))

Max Activating Token Index: 874

Text #7

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.6405. Min Act: -0.0000

Data Index: 331695 (C4 (Web Text))

Max Activating Token Index: 912

Text #8

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5732. Min Act: -0.0000

Data Index: 375409 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5772. Min Act: -0.0001

Data Index: 704184 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5970. Min Act: -0.0000

Data Index: 21683 (C4 (Web Text))

Max Activating Token Index: 799

Text #11

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5945. Min Act: -0.0001

Data Index: 94021 (C4 (Web Text))

Max Activating Token Index: 277

Text #12

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5883. Min Act: -0.0000

Data Index: 928537 (C4 (Web Text))

Max Activating Token Index: 15

Text #13

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5863. Min Act: -0.0001

Data Index: 1147657 (C4 (Web Text))

Max Activating Token Index: 112

Text #14

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5826. Min Act: -0.0000

Data Index: 268156 (C4 (Web Text))

Max Activating Token Index: 211

Text #15

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5657. Min Act: -0.0000

Data Index: 1273879 (C4 (Web Text))

Max Activating Token Index: 22

Text #16

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5891. Min Act: -0.0001

Data Index: 1119924 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5800. Min Act: -0.0001

Data Index: 99879 (C4 (Web Text))

Max Activating Token Index: 115

Text #18

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5753. Min Act: -0.0001

Data Index: 801065 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.7803. Min Range: -0.7803

Max Act: 0.5364. Min Act: -0.0001

Data Index: 1598523 (Python Code)

Max Activating Token Index: 764