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

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

Neuron 5532 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0849. Min Range: -2.0849

Max Act: 2.0849. Min Act: -0.0000

Data Index: 220442 (C4 (Web Text))

Max Activating Token Index: 934

Text #1

Max Range: 2.0849. Min Range: -2.0849

Max Act: 2.0531. Min Act: -0.0000

Data Index: 611597 (C4 (Web Text))

Max Activating Token Index: 730

Text #2

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.9993. Min Act: -0.0000

Data Index: 1035966 (C4 (Web Text))

Max Activating Token Index: 612

Text #3

Max Range: 2.0849. Min Range: -2.0849

Max Act: 2.0149. Min Act: -0.0000

Data Index: 649392 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.7009. Min Act: -0.0000

Data Index: 133520 (C4 (Web Text))

Max Activating Token Index: 987

Text #5

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.8589. Min Act: -0.0000

Data Index: 144177 (C4 (Web Text))

Max Activating Token Index: 484

Text #6

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.6643. Min Act: -0.0000

Data Index: 578422 (C4 (Web Text))

Max Activating Token Index: 646

Text #7

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.5671. Min Act: -0.0000

Data Index: 450115 (C4 (Web Text))

Max Activating Token Index: 595

Text #8

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.5457. Min Act: -0.0000

Data Index: 817118 (C4 (Web Text))

Max Activating Token Index: 487

Text #9

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.5377. Min Act: -0.0000

Data Index: 538844 (C4 (Web Text))

Max Activating Token Index: 444

Text #10

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.5304. Min Act: -0.0000

Data Index: 661791 (C4 (Web Text))

Max Activating Token Index: 929

Text #11

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.5176. Min Act: -0.0000

Data Index: 371584 (C4 (Web Text))

Max Activating Token Index: 129

Text #12

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.4770. Min Act: -0.0000

Data Index: 1309952 (C4 (Web Text))

Max Activating Token Index: 878

Text #13

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.4305. Min Act: -0.0000

Data Index: 580109 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.4307. Min Act: -0.0000

Data Index: 368641 (C4 (Web Text))

Max Activating Token Index: 87

Text #15

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.3988. Min Act: -0.0000

Data Index: 592511 (C4 (Web Text))

Max Activating Token Index: 711

Text #16

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.4726. Min Act: -0.0000

Data Index: 601934 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.4827. Min Act: -0.0000

Data Index: 1024520 (C4 (Web Text))

Max Activating Token Index: 117

Text #18

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.3765. Min Act: -0.0000

Data Index: 907287 (C4 (Web Text))

Max Activating Token Index: 282

Text #19

Max Range: 2.0849. Min Range: -2.0849

Max Act: 1.2665. Min Act: -0.0000

Data Index: 528268 (C4 (Web Text))

Max Activating Token Index: 67