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

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

Neuron 1351 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.1368. Min Act: -0.0000

Data Index: 79097 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 1.1368. Min Range: -1.1368

Max Act: 1.0914. Min Act: -0.0000

Data Index: 881183 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.9467. Min Act: 0.0000

Data Index: 1218285 (C4 (Web Text))

Max Activating Token Index: 441

Text #3

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8799. Min Act: -0.0000

Data Index: 68761 (C4 (Web Text))

Max Activating Token Index: 716

Text #4

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8572. Min Act: -0.0000

Data Index: 910160 (C4 (Web Text))

Max Activating Token Index: 296

Text #5

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8832. Min Act: -0.0000

Data Index: 1136746 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1265317 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7406. Min Act: 0.0001

Data Index: 1090477 (C4 (Web Text))

Max Activating Token Index: 622

Text #8

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7406. Min Act: -0.0000

Data Index: 326008 (C4 (Web Text))

Max Activating Token Index: 230

Text #9

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6750. Min Act: -0.0000

Data Index: 231986 (C4 (Web Text))

Max Activating Token Index: 308

Text #10

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7437. Min Act: -0.0000

Data Index: 694622 (C4 (Web Text))

Max Activating Token Index: 580

Text #11

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7400. Min Act: -0.0000

Data Index: 965324 (C4 (Web Text))

Max Activating Token Index: 283

Text #12

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.7670. Min Act: -0.0000

Data Index: 1135134 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6725. Min Act: -0.0000

Data Index: 519807 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6640. Min Act: -0.0000

Data Index: 591169 (C4 (Web Text))

Max Activating Token Index: 375

Text #15

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6335. Min Act: -0.0000

Data Index: 273489 (C4 (Web Text))

Max Activating Token Index: 197

Text #16

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6539. Min Act: -0.0000

Data Index: 810362 (C4 (Web Text))

Max Activating Token Index: 526

Text #17

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6224. Min Act: -0.0000

Data Index: 189173 (C4 (Web Text))

Max Activating Token Index: 668

Text #18

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6391. Min Act: -0.0000

Data Index: 1191150 (C4 (Web Text))

Max Activating Token Index: 769

Text #19

Max Range: 1.1368. Min Range: -1.1368

Max Act: 0.6677. Min Act: -0.0000

Data Index: 404627 (C4 (Web Text))

Max Activating Token Index: 537