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

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

Neuron 3435 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1791. Min Range: -2.1791

Max Act: 2.1791. Min Act: -0.0000

Data Index: 478839 (C4 (Web Text))

Max Activating Token Index: 364

Text #1

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.7157. Min Act: -0.0000

Data Index: 128934 (C4 (Web Text))

Max Activating Token Index: 455

Text #2

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.7982. Min Act: -0.0000

Data Index: 1098043 (C4 (Web Text))

Max Activating Token Index: 141

Text #3

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.7491. Min Act: -0.0000

Data Index: 679815 (C4 (Web Text))

Max Activating Token Index: 985

Text #4

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.7567. Min Act: -0.0000

Data Index: 876503 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.5924. Min Act: -0.0000

Data Index: 318454 (C4 (Web Text))

Max Activating Token Index: 696

Text #6

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.5735. Min Act: -0.0000

Data Index: 676938 (C4 (Web Text))

Max Activating Token Index: 764

Text #7

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.4729. Min Act: -0.0000

Data Index: 430359 (C4 (Web Text))

Max Activating Token Index: 735

Text #8

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.3523. Min Act: -0.0000

Data Index: 1134773 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.3861. Min Act: -0.0000

Data Index: 107152 (C4 (Web Text))

Max Activating Token Index: 750

Text #10

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.2961. Min Act: -0.0000

Data Index: 84298 (C4 (Web Text))

Max Activating Token Index: 839

Text #11

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.2875. Min Act: -0.0000

Data Index: 1024044 (C4 (Web Text))

Max Activating Token Index: 684

Text #12

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.2617. Min Act: -0.0000

Data Index: 317554 (C4 (Web Text))

Max Activating Token Index: 934

Text #13

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.3593. Min Act: -0.0000

Data Index: 872970 (C4 (Web Text))

Max Activating Token Index: 383

Text #14

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.2981. Min Act: -0.0000

Data Index: 880027 (C4 (Web Text))

Max Activating Token Index: 635

Text #15

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.2989. Min Act: -0.0000

Data Index: 637777 (C4 (Web Text))

Max Activating Token Index: 76

Text #16

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.3681. Min Act: -0.0000

Data Index: 766026 (C4 (Web Text))

Max Activating Token Index: 199

Text #17

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.2059. Min Act: -0.0000

Data Index: 1339388 (C4 (Web Text))

Max Activating Token Index: 263

Text #18

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.2517. Min Act: -0.0000

Data Index: 1311756 (C4 (Web Text))

Max Activating Token Index: 921

Text #19

Max Range: 2.1791. Min Range: -2.1791

Max Act: 1.1702. Min Act: -0.0000

Data Index: 40277 (C4 (Web Text))

Max Activating Token Index: 313