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

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

Neuron 1377 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: 4.1032. Min Range: -4.1032

Max Act: 4.1032. Min Act: -0.0000

Data Index: 398596 (C4 (Web Text))

Max Activating Token Index: 730

Text #1

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.8439. Min Act: -0.0000

Data Index: 349566 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.9852. Min Act: -0.0000

Data Index: 536748 (C4 (Web Text))

Max Activating Token Index: 533

Text #3

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.6902. Min Act: -0.0000

Data Index: 773469 (C4 (Web Text))

Max Activating Token Index: 545

Text #4

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.6050. Min Act: -0.0000

Data Index: 1068238 (C4 (Web Text))

Max Activating Token Index: 71

Text #5

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.6003. Min Act: -0.0000

Data Index: 147976 (C4 (Web Text))

Max Activating Token Index: 226

Text #6

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.6130. Min Act: -0.0000

Data Index: 1442805 (Python Code)

Max Activating Token Index: 19

Text #7

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.5909. Min Act: -0.0000

Data Index: 217175 (C4 (Web Text))

Max Activating Token Index: 363

Text #8

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.4058. Min Act: -0.0000

Data Index: 1291589 (C4 (Web Text))

Max Activating Token Index: 387

Text #9

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.3434. Min Act: -0.0000

Data Index: 1005077 (C4 (Web Text))

Max Activating Token Index: 948

Text #10

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.4247. Min Act: -0.0000

Data Index: 745422 (C4 (Web Text))

Max Activating Token Index: 494

Text #11

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.0431. Min Act: -0.0000

Data Index: 788971 (C4 (Web Text))

Max Activating Token Index: 771

Text #12

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.2036. Min Act: -0.0000

Data Index: 1523789 (Python Code)

Max Activating Token Index: 176

Text #13

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.2995. Min Act: -0.0000

Data Index: 327480 (C4 (Web Text))

Max Activating Token Index: 952

Text #14

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.1335. Min Act: -0.0000

Data Index: 641710 (C4 (Web Text))

Max Activating Token Index: 434

Text #15

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.0025. Min Act: -0.0000

Data Index: 903705 (C4 (Web Text))

Max Activating Token Index: 954

Text #16

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.0708. Min Act: -0.0000

Data Index: 1467310 (Python Code)

Max Activating Token Index: 86

Text #17

Max Range: 4.1032. Min Range: -4.1032

Max Act: 3.2024. Min Act: -0.0000

Data Index: 1594936 (Python Code)

Max Activating Token Index: 585

Text #18

Max Range: 4.1032. Min Range: -4.1032

Max Act: 2.9616. Min Act: -0.0000

Data Index: 1348794 (C4 (Web Text))

Max Activating Token Index: 793

Text #19

Max Range: 4.1032. Min Range: -4.1032

Max Act: 2.9055. Min Act: -0.0000

Data Index: 1254157 (C4 (Web Text))

Max Activating Token Index: 403