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

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

Neuron 5061 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4580. Min Act: -0.0000

Data Index: 723589 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.4380. Min Act: -0.0000

Data Index: 444975 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3808. Min Act: -0.0000

Data Index: 406237 (C4 (Web Text))

Max Activating Token Index: 752

Text #3

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3335. Min Act: -0.0000

Data Index: 823622 (C4 (Web Text))

Max Activating Token Index: 789

Text #4

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3176. Min Act: -0.0000

Data Index: 46670 (C4 (Web Text))

Max Activating Token Index: 794

Text #5

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2993. Min Act: -0.0000

Data Index: 676758 (C4 (Web Text))

Max Activating Token Index: 44

Text #6

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3096. Min Act: -0.0000

Data Index: 1299477 (C4 (Web Text))

Max Activating Token Index: 126

Text #7

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3062. Min Act: -0.0000

Data Index: 71984 (C4 (Web Text))

Max Activating Token Index: 77

Text #8

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.3009. Min Act: -0.0000

Data Index: 395005 (C4 (Web Text))

Max Activating Token Index: 364

Text #9

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2903. Min Act: -0.0000

Data Index: 642770 (C4 (Web Text))

Max Activating Token Index: 199

Text #10

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2767. Min Act: -0.0000

Data Index: 1082076 (C4 (Web Text))

Max Activating Token Index: 119

Text #11

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2666. Min Act: -0.0000

Data Index: 1222235 (C4 (Web Text))

Max Activating Token Index: 909

Text #12

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2877. Min Act: -0.0000

Data Index: 132146 (C4 (Web Text))

Max Activating Token Index: 448

Text #13

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2848. Min Act: -0.0000

Data Index: 900381 (C4 (Web Text))

Max Activating Token Index: 94

Text #14

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2800. Min Act: -0.0000

Data Index: 94467 (C4 (Web Text))

Max Activating Token Index: 962

Text #15

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2805. Min Act: -0.0000

Data Index: 56003 (C4 (Web Text))

Max Activating Token Index: 944

Text #16

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2710. Min Act: -0.0000

Data Index: 693104 (C4 (Web Text))

Max Activating Token Index: 950

Text #17

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2482. Min Act: -0.0000

Data Index: 898079 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2642. Min Act: -0.0000

Data Index: 760362 (C4 (Web Text))

Max Activating Token Index: 396

Text #19

Max Range: 0.4580. Min Range: -0.4580

Max Act: 0.2562. Min Act: -0.0000

Data Index: 825409 (C4 (Web Text))

Max Activating Token Index: 136