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

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

Neuron 4234 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.5167. Min Act: -0.0002

Data Index: 1055491 (C4 (Web Text))

Max Activating Token Index: 314

Text #1

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.5417. Min Act: -0.0002

Data Index: 1540910 (Python Code)

Max Activating Token Index: 882

Text #2

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.4876. Min Act: -0.0002

Data Index: 1640407 (Python Code)

Max Activating Token Index: 367

Text #3

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.4364. Min Act: -0.0002

Data Index: 1426787 (Python Code)

Max Activating Token Index: 934

Text #4

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.3140. Min Act: -0.0002

Data Index: 1431691 (Python Code)

Max Activating Token Index: 369

Text #5

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.3139. Min Act: -0.0002

Data Index: 1477947 (Python Code)

Max Activating Token Index: 73

Text #6

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.2643. Min Act: -0.0002

Data Index: 875301 (C4 (Web Text))

Max Activating Token Index: 691

Text #7

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1745. Min Act: -0.0002

Data Index: 136600 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.0596. Min Act: -0.0002

Data Index: 1381987 (Python Code)

Max Activating Token Index: 193

Text #9

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.2042. Min Act: -0.0002

Data Index: 1346393 (C4 (Web Text))

Max Activating Token Index: 287

Text #10

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1612. Min Act: -0.0002

Data Index: 1569871 (Python Code)

Max Activating Token Index: 599

Text #11

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.2647. Min Act: -0.0002

Data Index: 819703 (C4 (Web Text))

Max Activating Token Index: 366

Text #12

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1926. Min Act: -0.0002

Data Index: 926620 (C4 (Web Text))

Max Activating Token Index: 739

Text #13

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1621. Min Act: -0.0002

Data Index: 1647915 (Python Code)

Max Activating Token Index: 88

Text #14

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1207. Min Act: -0.0002

Data Index: 568094 (C4 (Web Text))

Max Activating Token Index: 723

Text #15

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1114. Min Act: -0.0002

Data Index: 472620 (C4 (Web Text))

Max Activating Token Index: 489

Text #16

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1095. Min Act: -0.0002

Data Index: 124114 (C4 (Web Text))

Max Activating Token Index: 842

Text #17

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.1160. Min Act: -0.0002

Data Index: 1386064 (Python Code)

Max Activating Token Index: 594

Text #18

Max Range: 1.5417. Min Range: -1.5417

Max Act: 0.9932. Min Act: -0.0002

Data Index: 1603247 (Python Code)

Max Activating Token Index: 186

Text #19

Max Range: 1.5417. Min Range: -1.5417

Max Act: 1.0885. Min Act: -0.0002

Data Index: 1493653 (Python Code)

Max Activating Token Index: 257