Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 652 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.9730. Min Act: -0.0000

Data Index: 1280053 (C4 (Web Text))

Max Activating Token Index: 876

Text #1

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8980. Min Act: -0.0000

Data Index: 1025691 (C4 (Web Text))

Max Activating Token Index: 149

Text #2

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8625. Min Act: -0.0000

Data Index: 225269 (C4 (Web Text))

Max Activating Token Index: 950

Text #3

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8883. Min Act: -0.0000

Data Index: 533586 (C4 (Web Text))

Max Activating Token Index: 265

Text #4

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8150. Min Act: -0.0000

Data Index: 210841 (C4 (Web Text))

Max Activating Token Index: 847

Text #5

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8590. Min Act: -0.0000

Data Index: 540986 (C4 (Web Text))

Max Activating Token Index: 719

Text #6

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8296. Min Act: -0.0000

Data Index: 989188 (C4 (Web Text))

Max Activating Token Index: 906

Text #7

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8264. Min Act: -0.0000

Data Index: 835628 (C4 (Web Text))

Max Activating Token Index: 926

Text #8

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1245491 (C4 (Web Text))

Max Activating Token Index: 511

Text #9

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8272. Min Act: -0.0000

Data Index: 241769 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8370. Min Act: -0.0000

Data Index: 1186498 (C4 (Web Text))

Max Activating Token Index: 457

Text #11

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1354714 (C4 (Web Text))

Max Activating Token Index: 850

Text #12

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.7426. Min Act: -0.0000

Data Index: 883642 (C4 (Web Text))

Max Activating Token Index: 891

Text #13

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.7317. Min Act: -0.0000

Data Index: 1080992 (C4 (Web Text))

Max Activating Token Index: 74

Text #14

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.7135. Min Act: -0.0000

Data Index: 1029092 (C4 (Web Text))

Max Activating Token Index: 232

Text #15

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1011616 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.7077. Min Act: -0.0000

Data Index: 82145 (C4 (Web Text))

Max Activating Token Index: 445

Text #17

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.7023. Min Act: -0.0000

Data Index: 1566013 (Python Code)

Max Activating Token Index: 483

Text #18

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.6761. Min Act: -0.0000

Data Index: 829746 (C4 (Web Text))

Max Activating Token Index: 208

Text #19

Max Range: 0.9730. Min Range: -0.9730

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1321905 (C4 (Web Text))

Max Activating Token Index: 82