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

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

Neuron 5597 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: 4.9919. Min Range: -4.9919

Max Act: 4.9919. Min Act: -0.0000

Data Index: 1043560 (C4 (Web Text))

Max Activating Token Index: 688

Text #1

Max Range: 4.9919. Min Range: -4.9919

Max Act: 4.9429. Min Act: -0.0000

Data Index: 774817 (C4 (Web Text))

Max Activating Token Index: 421

Text #2

Max Range: 4.9919. Min Range: -4.9919

Max Act: 4.4841. Min Act: -0.0000

Data Index: 451221 (C4 (Web Text))

Max Activating Token Index: 240

Text #3

Max Range: 4.9919. Min Range: -4.9919

Max Act: 4.6198. Min Act: -0.0000

Data Index: 903644 (C4 (Web Text))

Max Activating Token Index: 503

Text #4

Max Range: 4.9919. Min Range: -4.9919

Max Act: 4.1216. Min Act: -0.0000

Data Index: 1237009 (C4 (Web Text))

Max Activating Token Index: 203

Text #5

Max Range: 4.9919. Min Range: -4.9919

Max Act: 4.0599. Min Act: -0.0000

Data Index: 393747 (C4 (Web Text))

Max Activating Token Index: 332

Text #6

Max Range: 4.9919. Min Range: -4.9919

Max Act: 4.0509. Min Act: -0.0000

Data Index: 155825 (C4 (Web Text))

Max Activating Token Index: 186

Text #7

Max Range: 4.9919. Min Range: -4.9919

Max Act: 4.3086. Min Act: -0.0000

Data Index: 511632 (C4 (Web Text))

Max Activating Token Index: 883

Text #8

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.9365. Min Act: -0.0000

Data Index: 675578 (C4 (Web Text))

Max Activating Token Index: 152

Text #9

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.8608. Min Act: -0.0000

Data Index: 1103213 (C4 (Web Text))

Max Activating Token Index: 674

Text #10

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.9654. Min Act: -0.0000

Data Index: 674545 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.9682. Min Act: -0.0000

Data Index: 1094686 (C4 (Web Text))

Max Activating Token Index: 343

Text #12

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.8474. Min Act: -0.0000

Data Index: 470456 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.9455. Min Act: -0.0000

Data Index: 522833 (C4 (Web Text))

Max Activating Token Index: 856

Text #14

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.8050. Min Act: -0.0000

Data Index: 235113 (C4 (Web Text))

Max Activating Token Index: 682

Text #15

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.5241. Min Act: -0.0000

Data Index: 1214247 (C4 (Web Text))

Max Activating Token Index: 279

Text #16

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.6564. Min Act: -0.0000

Data Index: 229809 (C4 (Web Text))

Max Activating Token Index: 776

Text #17

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.6536. Min Act: -0.0000

Data Index: 462870 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.6267. Min Act: -0.0000

Data Index: 1333576 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 4.9919. Min Range: -4.9919

Max Act: 3.3841. Min Act: -0.0000

Data Index: 1109444 (C4 (Web Text))

Max Activating Token Index: 196