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

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

Neuron 5096 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2461. Min Act: -0.0002

Data Index: 819912 (C4 (Web Text))

Max Activating Token Index: 584

Text #1

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2357. Min Act: -0.0002

Data Index: 88107 (C4 (Web Text))

Max Activating Token Index: 428

Text #2

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2176. Min Act: -0.0002

Data Index: 633985 (C4 (Web Text))

Max Activating Token Index: 269

Text #3

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2157. Min Act: -0.0002

Data Index: 369911 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2370. Min Act: -0.0002

Data Index: 602819 (C4 (Web Text))

Max Activating Token Index: 873

Text #5

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2354. Min Act: -0.0002

Data Index: 116772 (C4 (Web Text))

Max Activating Token Index: 359

Text #6

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2413. Min Act: -0.0002

Data Index: 399716 (C4 (Web Text))

Max Activating Token Index: 571

Text #7

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2222. Min Act: -0.0002

Data Index: 245501 (C4 (Web Text))

Max Activating Token Index: 325

Text #8

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2125. Min Act: -0.0002

Data Index: 752969 (C4 (Web Text))

Max Activating Token Index: 313

Text #9

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2114. Min Act: -0.0002

Data Index: 621335 (C4 (Web Text))

Max Activating Token Index: 797

Text #10

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2130. Min Act: -0.0002

Data Index: 1076823 (C4 (Web Text))

Max Activating Token Index: 845

Text #11

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2074. Min Act: -0.0002

Data Index: 287475 (C4 (Web Text))

Max Activating Token Index: 711

Text #12

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2257. Min Act: -0.0002

Data Index: 458820 (C4 (Web Text))

Max Activating Token Index: 395

Text #13

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2076. Min Act: -0.0002

Data Index: 713148 (C4 (Web Text))

Max Activating Token Index: 211

Text #14

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2051. Min Act: -0.0002

Data Index: 443724 (C4 (Web Text))

Max Activating Token Index: 269

Text #15

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1906. Min Act: -0.0002

Data Index: 426124 (C4 (Web Text))

Max Activating Token Index: 942

Text #16

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2130. Min Act: -0.0002

Data Index: 1306730 (C4 (Web Text))

Max Activating Token Index: 239

Text #17

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1828. Min Act: -0.0002

Data Index: 1126322 (C4 (Web Text))

Max Activating Token Index: 908

Text #18

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.1769. Min Act: -0.0002

Data Index: 1114787 (C4 (Web Text))

Max Activating Token Index: 405

Text #19

Max Range: 0.2461. Min Range: -0.2461

Max Act: 0.2041. Min Act: -0.0002

Data Index: 1318286 (C4 (Web Text))

Max Activating Token Index: 749