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

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

Neuron 4859 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.9853. Min Act: -0.0001

Data Index: 675276 (C4 (Web Text))

Max Activating Token Index: 624

Text #1

Max Range: 1.0866. Min Range: -1.0866

Max Act: 1.0866. Min Act: -0.0001

Data Index: 96392 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8954. Min Act: -0.0001

Data Index: 1139013 (C4 (Web Text))

Max Activating Token Index: 856

Text #3

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8674. Min Act: -0.0001

Data Index: 402104 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.9509. Min Act: -0.0001

Data Index: 429781 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8827. Min Act: -0.0001

Data Index: 454354 (C4 (Web Text))

Max Activating Token Index: 381

Text #6

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.9121. Min Act: -0.0001

Data Index: 1106622 (C4 (Web Text))

Max Activating Token Index: 93

Text #7

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.9121. Min Act: -0.0001

Data Index: 295709 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8725. Min Act: -0.0001

Data Index: 958872 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8349. Min Act: -0.0001

Data Index: 607891 (C4 (Web Text))

Max Activating Token Index: 397

Text #10

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8254. Min Act: -0.0001

Data Index: 710950 (C4 (Web Text))

Max Activating Token Index: 2

Text #11

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8169. Min Act: -0.0001

Data Index: 108078 (C4 (Web Text))

Max Activating Token Index: 24

Text #12

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7730. Min Act: -0.0001

Data Index: 1063696 (C4 (Web Text))

Max Activating Token Index: 219

Text #13

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8092. Min Act: -0.0000

Data Index: 1391875 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.9557. Min Act: -0.0001

Data Index: 850890 (C4 (Web Text))

Max Activating Token Index: 874

Text #15

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8480. Min Act: -0.0001

Data Index: 956362 (C4 (Web Text))

Max Activating Token Index: 126

Text #16

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7522. Min Act: -0.0001

Data Index: 1246290 (C4 (Web Text))

Max Activating Token Index: 649

Text #17

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.8098. Min Act: -0.0001

Data Index: 540663 (C4 (Web Text))

Max Activating Token Index: 998

Text #18

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7709. Min Act: -0.0001

Data Index: 2611 (C4 (Web Text))

Max Activating Token Index: 759

Text #19

Max Range: 1.0866. Min Range: -1.0866

Max Act: 0.7787. Min Act: -0.0001

Data Index: 692734 (C4 (Web Text))

Max Activating Token Index: 2