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

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

Neuron 4582 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.6345. Min Act: -0.0000

Data Index: 868889 (C4 (Web Text))

Max Activating Token Index: 321

Text #1

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.5352. Min Act: -0.0000

Data Index: 568122 (C4 (Web Text))

Max Activating Token Index: 457

Text #2

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.4060. Min Act: -0.0000

Data Index: 99211 (C4 (Web Text))

Max Activating Token Index: 565

Text #3

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2135. Min Act: -0.0000

Data Index: 1242444 (C4 (Web Text))

Max Activating Token Index: 967

Text #4

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2912. Min Act: -0.0000

Data Index: 86976 (C4 (Web Text))

Max Activating Token Index: 544

Text #5

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1711. Min Act: -0.0000

Data Index: 132492 (C4 (Web Text))

Max Activating Token Index: 793

Text #6

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2759. Min Act: -0.0000

Data Index: 587818 (C4 (Web Text))

Max Activating Token Index: 290

Text #7

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1861. Min Act: -0.0000

Data Index: 482575 (C4 (Web Text))

Max Activating Token Index: 524

Text #8

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1805. Min Act: -0.0000

Data Index: 908827 (C4 (Web Text))

Max Activating Token Index: 39

Text #9

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2031. Min Act: -0.0000

Data Index: 937007 (C4 (Web Text))

Max Activating Token Index: 896

Text #10

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1175. Min Act: -0.0000

Data Index: 585948 (C4 (Web Text))

Max Activating Token Index: 370

Text #11

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1429. Min Act: -0.0000

Data Index: 819890 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.2051. Min Act: -0.0000

Data Index: 86945 (C4 (Web Text))

Max Activating Token Index: 695

Text #13

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1497. Min Act: -0.0000

Data Index: 806053 (C4 (Web Text))

Max Activating Token Index: 183

Text #14

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1196404 (C4 (Web Text))

Max Activating Token Index: 640

Text #15

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0097. Min Act: -0.0000

Data Index: 385506 (C4 (Web Text))

Max Activating Token Index: 753

Text #16

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0913. Min Act: -0.0000

Data Index: 781856 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1605. Min Act: -0.0000

Data Index: 1184893 (C4 (Web Text))

Max Activating Token Index: 503

Text #18

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.1130. Min Act: -0.0000

Data Index: 372121 (C4 (Web Text))

Max Activating Token Index: 614

Text #19

Max Range: 1.6345. Min Range: -1.6345

Max Act: 1.0842. Min Act: -0.0000

Data Index: 309359 (C4 (Web Text))

Max Activating Token Index: 448