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

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

Neuron 2437 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: 1.7341. Min Range: -1.7341

Max Act: 1.7341. Min Act: -0.0002

Data Index: 951071 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.5154. Min Act: -0.0002

Data Index: 1341161 (C4 (Web Text))

Max Activating Token Index: 261

Text #2

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.2253. Min Act: -0.0002

Data Index: 735723 (C4 (Web Text))

Max Activating Token Index: 152

Text #3

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.3663. Min Act: -0.0002

Data Index: 817038 (C4 (Web Text))

Max Activating Token Index: 971

Text #4

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.2688. Min Act: -0.0002

Data Index: 1311408 (C4 (Web Text))

Max Activating Token Index: 239

Text #5

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.2743. Min Act: -0.0002

Data Index: 619555 (C4 (Web Text))

Max Activating Token Index: 543

Text #6

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.1516. Min Act: -0.0002

Data Index: 534985 (C4 (Web Text))

Max Activating Token Index: 366

Text #7

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.1724. Min Act: -0.0002

Data Index: 1096442 (C4 (Web Text))

Max Activating Token Index: 709

Text #8

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.0540. Min Act: -0.0002

Data Index: 1050064 (C4 (Web Text))

Max Activating Token Index: 617

Text #9

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.2286. Min Act: -0.0002

Data Index: 564176 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.0882. Min Act: -0.0002

Data Index: 255762 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.1173. Min Act: -0.0002

Data Index: 790454 (C4 (Web Text))

Max Activating Token Index: 971

Text #12

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.1404. Min Act: -0.0002

Data Index: 818880 (C4 (Web Text))

Max Activating Token Index: 139

Text #13

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.1063. Min Act: -0.0002

Data Index: 1214120 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 1.7341. Min Range: -1.7341

Max Act: 0.9669. Min Act: -0.0002

Data Index: 518985 (C4 (Web Text))

Max Activating Token Index: 590

Text #15

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.1484. Min Act: -0.0002

Data Index: 660070 (C4 (Web Text))

Max Activating Token Index: 546

Text #16

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.1358. Min Act: -0.0002

Data Index: 1313007 (C4 (Web Text))

Max Activating Token Index: 235

Text #17

Max Range: 1.7341. Min Range: -1.7341

Max Act: 0.9355. Min Act: -0.0002

Data Index: 1255565 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.2252. Min Act: -0.0002

Data Index: 481264 (C4 (Web Text))

Max Activating Token Index: 864

Text #19

Max Range: 1.7341. Min Range: -1.7341

Max Act: 1.1265. Min Act: -0.0002

Data Index: 876362 (C4 (Web Text))

Max Activating Token Index: 771