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

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

Neuron 3350 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: 0.2804. Min Range: -0.2804

Max Act: 0.2513. Min Act: -0.0000

Data Index: 126922 (C4 (Web Text))

Max Activating Token Index: 638

Text #1

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.2804. Min Act: -0.0000

Data Index: 483385 (C4 (Web Text))

Max Activating Token Index: 749

Text #2

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.2085. Min Act: -0.0000

Data Index: 1163294 (C4 (Web Text))

Max Activating Token Index: 628

Text #3

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.2046. Min Act: -0.0000

Data Index: 598707 (C4 (Web Text))

Max Activating Token Index: 214

Text #4

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1980. Min Act: -0.0000

Data Index: 692820 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1958. Min Act: -0.0000

Data Index: 927033 (C4 (Web Text))

Max Activating Token Index: 48

Text #6

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1945. Min Act: -0.0000

Data Index: 687624 (C4 (Web Text))

Max Activating Token Index: 76

Text #7

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1730. Min Act: -0.0000

Data Index: 569845 (C4 (Web Text))

Max Activating Token Index: 286

Text #8

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1816. Min Act: -0.0000

Data Index: 12476 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1667. Min Act: -0.0000

Data Index: 1200445 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1646. Min Act: -0.0000

Data Index: 1034735 (C4 (Web Text))

Max Activating Token Index: 970

Text #11

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1720. Min Act: -0.0000

Data Index: 708639 (C4 (Web Text))

Max Activating Token Index: 143

Text #12

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1943. Min Act: -0.0000

Data Index: 663832 (C4 (Web Text))

Max Activating Token Index: 187

Text #13

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1739. Min Act: -0.0000

Data Index: 1150438 (C4 (Web Text))

Max Activating Token Index: 708

Text #14

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1665. Min Act: -0.0000

Data Index: 998291 (C4 (Web Text))

Max Activating Token Index: 163

Text #15

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1630. Min Act: -0.0000

Data Index: 153863 (C4 (Web Text))

Max Activating Token Index: 732

Text #16

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1605. Min Act: -0.0000

Data Index: 762456 (C4 (Web Text))

Max Activating Token Index: 497

Text #17

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1501. Min Act: -0.0000

Data Index: 451143 (C4 (Web Text))

Max Activating Token Index: 78

Text #18

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1592. Min Act: -0.0000

Data Index: 11155 (C4 (Web Text))

Max Activating Token Index: 640

Text #19

Max Range: 0.2804. Min Range: -0.2804

Max Act: 0.1626. Min Act: -0.0000

Data Index: 1089601 (C4 (Web Text))

Max Activating Token Index: 173