Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4289 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2741. Min Act: -0.0000

Data Index: 962245 (C4 (Web Text))

Max Activating Token Index: 324

Text #1

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2402. Min Act: -0.0000

Data Index: 579974 (C4 (Web Text))

Max Activating Token Index: 206

Text #2

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2347. Min Act: -0.0000

Data Index: 909741 (C4 (Web Text))

Max Activating Token Index: 587

Text #3

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2129. Min Act: -0.0000

Data Index: 1088962 (C4 (Web Text))

Max Activating Token Index: 101

Text #4

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2070. Min Act: -0.0000

Data Index: 150888 (C4 (Web Text))

Max Activating Token Index: 939

Text #5

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.2091. Min Act: -0.0000

Data Index: 510912 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1977. Min Act: -0.0000

Data Index: 282842 (C4 (Web Text))

Max Activating Token Index: 433

Text #7

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1923. Min Act: -0.0000

Data Index: 234152 (C4 (Web Text))

Max Activating Token Index: 265

Text #8

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1858. Min Act: -0.0000

Data Index: 404244 (C4 (Web Text))

Max Activating Token Index: 747

Text #9

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1996. Min Act: -0.0000

Data Index: 966303 (C4 (Web Text))

Max Activating Token Index: 945

Text #10

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1888. Min Act: -0.0000

Data Index: 615014 (C4 (Web Text))

Max Activating Token Index: 622

Text #11

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1020307 (C4 (Web Text))

Max Activating Token Index: 546

Text #12

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1838. Min Act: -0.0000

Data Index: 823387 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1928. Min Act: -0.0000

Data Index: 496690 (C4 (Web Text))

Max Activating Token Index: 592

Text #14

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1840. Min Act: -0.0000

Data Index: 878951 (C4 (Web Text))

Max Activating Token Index: 393

Text #15

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1835. Min Act: -0.0000

Data Index: 1031303 (C4 (Web Text))

Max Activating Token Index: 225

Text #16

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1779. Min Act: -0.0000

Data Index: 637405 (C4 (Web Text))

Max Activating Token Index: 825

Text #17

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1770. Min Act: -0.0000

Data Index: 1005066 (C4 (Web Text))

Max Activating Token Index: 299

Text #18

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1870. Min Act: -0.0000

Data Index: 58998 (C4 (Web Text))

Max Activating Token Index: 414

Text #19

Max Range: 0.2741. Min Range: -0.2741

Max Act: 0.1798. Min Act: -0.0000

Data Index: 1161500 (C4 (Web Text))

Max Activating Token Index: 591