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

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

Neuron 2046 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2068. Min Range: -2.2068

Max Act: 2.2068. Min Act: -0.0000

Data Index: 786758 (C4 (Web Text))

Max Activating Token Index: 649

Text #1

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.7833. Min Act: -0.0000

Data Index: 494123 (C4 (Web Text))

Max Activating Token Index: 956

Text #2

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.6108. Min Act: -0.0000

Data Index: 224433 (C4 (Web Text))

Max Activating Token Index: 724

Text #3

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.2531. Min Act: -0.0000

Data Index: 320385 (C4 (Web Text))

Max Activating Token Index: 636

Text #4

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.3824. Min Act: -0.0000

Data Index: 583567 (C4 (Web Text))

Max Activating Token Index: 700

Text #5

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.2472. Min Act: -0.0000

Data Index: 142469 (C4 (Web Text))

Max Activating Token Index: 936

Text #6

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.2437. Min Act: -0.0000

Data Index: 834996 (C4 (Web Text))

Max Activating Token Index: 567

Text #7

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.2819. Min Act: -0.0000

Data Index: 713758 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.2068. Min Act: -0.0000

Data Index: 1047948 (C4 (Web Text))

Max Activating Token Index: 832

Text #9

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.1847. Min Act: -0.0000

Data Index: 1167208 (C4 (Web Text))

Max Activating Token Index: 654

Text #10

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.1840. Min Act: -0.0000

Data Index: 1246719 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.1099. Min Act: -0.0000

Data Index: 618425 (C4 (Web Text))

Max Activating Token Index: 786

Text #12

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.2463. Min Act: -0.0000

Data Index: 820026 (C4 (Web Text))

Max Activating Token Index: 226

Text #13

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.0959. Min Act: -0.0000

Data Index: 1243667 (C4 (Web Text))

Max Activating Token Index: 421

Text #14

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.1080. Min Act: -0.0000

Data Index: 82316 (C4 (Web Text))

Max Activating Token Index: 956

Text #15

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.0990. Min Act: -0.0000

Data Index: 974954 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.0169. Min Act: -0.0000

Data Index: 839529 (C4 (Web Text))

Max Activating Token Index: 934

Text #17

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.1500. Min Act: -0.0000

Data Index: 96239 (C4 (Web Text))

Max Activating Token Index: 895

Text #18

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.1490. Min Act: -0.0000

Data Index: 52533 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 2.2068. Min Range: -2.2068

Max Act: 1.0559. Min Act: -0.0000

Data Index: 1481007 (Python Code)

Max Activating Token Index: 775