Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2797 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2368. Min Act: -0.0001

Data Index: 115850 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2132. Min Act: -0.0002

Data Index: 6999 (C4 (Web Text))

Max Activating Token Index: 645

Text #2

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2265. Min Act: -0.0001

Data Index: 70861 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2284. Min Act: -0.0001

Data Index: 473521 (C4 (Web Text))

Max Activating Token Index: 980

Text #4

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2283. Min Act: -0.0002

Data Index: 347410 (C4 (Web Text))

Max Activating Token Index: 155

Text #5

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2263. Min Act: -0.0001

Data Index: 414892 (C4 (Web Text))

Max Activating Token Index: 454

Text #6

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2180. Min Act: -0.0001

Data Index: 119285 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2124. Min Act: -0.0002

Data Index: 567633 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2184. Min Act: -0.0001

Data Index: 416806 (C4 (Web Text))

Max Activating Token Index: 403

Text #9

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2084. Min Act: -0.0001

Data Index: 1021417 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2195. Min Act: -0.0002

Data Index: 674541 (C4 (Web Text))

Max Activating Token Index: 883

Text #11

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1926. Min Act: -0.0001

Data Index: 868775 (C4 (Web Text))

Max Activating Token Index: 465

Text #12

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1999. Min Act: -0.0002

Data Index: 9745 (C4 (Web Text))

Max Activating Token Index: 300

Text #13

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1852. Min Act: -0.0002

Data Index: 1145502 (C4 (Web Text))

Max Activating Token Index: 713

Text #14

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.2034. Min Act: -0.0002

Data Index: 154640 (C4 (Web Text))

Max Activating Token Index: 63

Text #15

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1923. Min Act: -0.0001

Data Index: 1072963 (C4 (Web Text))

Max Activating Token Index: 86

Text #16

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1914. Min Act: -0.0001

Data Index: 294286 (C4 (Web Text))

Max Activating Token Index: 11

Text #17

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1915. Min Act: -0.0001

Data Index: 678934 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1868. Min Act: -0.0001

Data Index: 209012 (C4 (Web Text))

Max Activating Token Index: 690

Text #19

Max Range: 0.2368. Min Range: -0.2368

Max Act: 0.1817. Min Act: -0.0001

Data Index: 591751 (C4 (Web Text))

Max Activating Token Index: 250