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

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

Neuron 1492 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: 4.6939. Min Range: -4.6939

Max Act: 4.6939. Min Act: -0.0000

Data Index: 1612746 (Python Code)

Max Activating Token Index: 280

Text #1

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.5895. Min Act: -0.0000

Data Index: 782684 (C4 (Web Text))

Max Activating Token Index: 989

Text #2

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.5121. Min Act: -0.0000

Data Index: 1361877 (Python Code)

Max Activating Token Index: 944

Text #3

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.1717. Min Act: -0.0000

Data Index: 1556795 (Python Code)

Max Activating Token Index: 718

Text #4

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.4434. Min Act: -0.0000

Data Index: 1363290 (Python Code)

Max Activating Token Index: 956

Text #5

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.2186. Min Act: -0.0000

Data Index: 207729 (C4 (Web Text))

Max Activating Token Index: 33

Text #6

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.2016. Min Act: -0.0000

Data Index: 1424068 (Python Code)

Max Activating Token Index: 673

Text #7

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.1431. Min Act: -0.0000

Data Index: 1453718 (Python Code)

Max Activating Token Index: 724

Text #8

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.1198. Min Act: -0.0000

Data Index: 1195375 (C4 (Web Text))

Max Activating Token Index: 752

Text #9

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.2419. Min Act: -0.0000

Data Index: 1545082 (Python Code)

Max Activating Token Index: 8

Text #10

Max Range: 4.6939. Min Range: -4.6939

Max Act: 2.9447. Min Act: -0.0000

Data Index: 237281 (C4 (Web Text))

Max Activating Token Index: 238

Text #11

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.0803. Min Act: -0.0000

Data Index: 1446308 (Python Code)

Max Activating Token Index: 729

Text #12

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.1552. Min Act: -0.0000

Data Index: 1621860 (Python Code)

Max Activating Token Index: 1021

Text #13

Max Range: 4.6939. Min Range: -4.6939

Max Act: 3.0164. Min Act: -0.0000

Data Index: 1563449 (Python Code)

Max Activating Token Index: 965

Text #14

Max Range: 4.6939. Min Range: -4.6939

Max Act: 2.8690. Min Act: -0.0000

Data Index: 1476705 (Python Code)

Max Activating Token Index: 945

Text #15

Max Range: 4.6939. Min Range: -4.6939

Max Act: 2.7093. Min Act: -0.0000

Data Index: 366564 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 4.6939. Min Range: -4.6939

Max Act: 2.9812. Min Act: -0.0000

Data Index: 1392651 (Python Code)

Max Activating Token Index: 158

Text #17

Max Range: 4.6939. Min Range: -4.6939

Max Act: 2.6811. Min Act: -0.0000

Data Index: 285708 (C4 (Web Text))

Max Activating Token Index: 317

Text #18

Max Range: 4.6939. Min Range: -4.6939

Max Act: 2.9588. Min Act: -0.0000

Data Index: 1418156 (Python Code)

Max Activating Token Index: 109

Text #19

Max Range: 4.6939. Min Range: -4.6939

Max Act: 2.9543. Min Act: -0.0000

Data Index: 931717 (C4 (Web Text))

Max Activating Token Index: 326