Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1988 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2311. Min Act: -0.0003

Data Index: 924799 (C4 (Web Text))

Max Activating Token Index: 219

Text #1

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2050. Min Act: -0.0004

Data Index: 840303 (C4 (Web Text))

Max Activating Token Index: 383

Text #2

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2125. Min Act: -0.0003

Data Index: 1292694 (C4 (Web Text))

Max Activating Token Index: 405

Text #3

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2018. Min Act: -0.0003

Data Index: 322577 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.2000. Min Act: -0.0003

Data Index: 756206 (C4 (Web Text))

Max Activating Token Index: 365

Text #5

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1938. Min Act: -0.0003

Data Index: 480648 (C4 (Web Text))

Max Activating Token Index: 883

Text #6

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1973. Min Act: -0.0003

Data Index: 536882 (C4 (Web Text))

Max Activating Token Index: 692

Text #7

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1883. Min Act: -0.0003

Data Index: 1106872 (C4 (Web Text))

Max Activating Token Index: 847

Text #8

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1900. Min Act: -0.0003

Data Index: 849148 (C4 (Web Text))

Max Activating Token Index: 595

Text #9

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1858. Min Act: -0.0003

Data Index: 461167 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1974. Min Act: -0.0003

Data Index: 394836 (C4 (Web Text))

Max Activating Token Index: 854

Text #11

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1921. Min Act: -0.0004

Data Index: 1022684 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1926. Min Act: -0.0003

Data Index: 217005 (C4 (Web Text))

Max Activating Token Index: 501

Text #13

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1895. Min Act: -0.0004

Data Index: 1163300 (C4 (Web Text))

Max Activating Token Index: 387

Text #14

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1951. Min Act: -0.0004

Data Index: 1133569 (C4 (Web Text))

Max Activating Token Index: 578

Text #15

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1908. Min Act: -0.0003

Data Index: 490607 (C4 (Web Text))

Max Activating Token Index: 609

Text #16

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1948. Min Act: -0.0003

Data Index: 183463 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1902. Min Act: -0.0003

Data Index: 1282399 (C4 (Web Text))

Max Activating Token Index: 174

Text #18

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1874. Min Act: -0.0003

Data Index: 393858 (C4 (Web Text))

Max Activating Token Index: 959

Text #19

Max Range: 0.2311. Min Range: -0.2311

Max Act: 0.1813. Min Act: -0.0003

Data Index: 1191403 (C4 (Web Text))

Max Activating Token Index: 989