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

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

Neuron 3825 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.9707. Min Act: -0.0000

Data Index: 104253 (C4 (Web Text))

Max Activating Token Index: 881

Text #1

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.8377. Min Act: -0.0000

Data Index: 287895 (C4 (Web Text))

Max Activating Token Index: 293

Text #2

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7587. Min Act: -0.0000

Data Index: 409722 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7116. Min Act: -0.0000

Data Index: 948278 (C4 (Web Text))

Max Activating Token Index: 969

Text #4

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.7094. Min Act: -0.0000

Data Index: 1175028 (C4 (Web Text))

Max Activating Token Index: 807

Text #5

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1141780 (C4 (Web Text))

Max Activating Token Index: 43

Text #6

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.6535. Min Act: -0.0000

Data Index: 875695 (C4 (Web Text))

Max Activating Token Index: 393

Text #7

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5895. Min Act: -0.0000

Data Index: 1277628 (C4 (Web Text))

Max Activating Token Index: 644

Text #8

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.6103. Min Act: -0.0000

Data Index: 725460 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5611. Min Act: -0.0000

Data Index: 1298360 (C4 (Web Text))

Max Activating Token Index: 269

Text #10

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5765. Min Act: -0.0000

Data Index: 154511 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.6181. Min Act: -0.0000

Data Index: 1359304 (C4 (Web Text))

Max Activating Token Index: 571

Text #12

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5525. Min Act: -0.0000

Data Index: 341626 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5854. Min Act: -0.0000

Data Index: 1255542 (C4 (Web Text))

Max Activating Token Index: 378

Text #14

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.6055. Min Act: -0.0000

Data Index: 917502 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5641. Min Act: -0.0000

Data Index: 468975 (C4 (Web Text))

Max Activating Token Index: 397

Text #16

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5863. Min Act: -0.0000

Data Index: 1087029 (C4 (Web Text))

Max Activating Token Index: 915

Text #17

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5953. Min Act: -0.0000

Data Index: 910684 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5646. Min Act: -0.0000

Data Index: 681350 (C4 (Web Text))

Max Activating Token Index: 425

Text #19

Max Range: 0.9707. Min Range: -0.9707

Max Act: 0.5584. Min Act: -0.0000

Data Index: 139881 (C4 (Web Text))

Max Activating Token Index: 34