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

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

Neuron 2301 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: 0.1813. Min Range: -0.1813

Max Act: 0.1729. Min Act: -0.0002

Data Index: 868551 (C4 (Web Text))

Max Activating Token Index: 436

Text #1

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1686. Min Act: -0.0002

Data Index: 1169844 (C4 (Web Text))

Max Activating Token Index: 931

Text #2

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1649. Min Act: -0.0002

Data Index: 995626 (C4 (Web Text))

Max Activating Token Index: 91

Text #3

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1813. Min Act: -0.0002

Data Index: 1252269 (C4 (Web Text))

Max Activating Token Index: 880

Text #4

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1667. Min Act: -0.0002

Data Index: 771171 (C4 (Web Text))

Max Activating Token Index: 478

Text #5

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1364. Min Act: -0.0002

Data Index: 1045196 (C4 (Web Text))

Max Activating Token Index: 336

Text #6

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1426. Min Act: -0.0002

Data Index: 331993 (C4 (Web Text))

Max Activating Token Index: 275

Text #7

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1316. Min Act: -0.0002

Data Index: 1489040 (Python Code)

Max Activating Token Index: 559

Text #8

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1629. Min Act: -0.0002

Data Index: 779108 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1446. Min Act: -0.0002

Data Index: 362848 (C4 (Web Text))

Max Activating Token Index: 352

Text #10

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1143. Min Act: -0.0003

Data Index: 693667 (C4 (Web Text))

Max Activating Token Index: 234

Text #11

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1100. Min Act: -0.0002

Data Index: 1326483 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1166. Min Act: -0.0002

Data Index: 941146 (C4 (Web Text))

Max Activating Token Index: 266

Text #13

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1115. Min Act: -0.0002

Data Index: 933096 (C4 (Web Text))

Max Activating Token Index: 692

Text #14

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1317. Min Act: -0.0002

Data Index: 488132 (C4 (Web Text))

Max Activating Token Index: 429

Text #15

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1465. Min Act: -0.0002

Data Index: 45659 (C4 (Web Text))

Max Activating Token Index: 189

Text #16

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1172. Min Act: -0.0002

Data Index: 446289 (C4 (Web Text))

Max Activating Token Index: 339

Text #17

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1307. Min Act: -0.0002

Data Index: 997890 (C4 (Web Text))

Max Activating Token Index: 576

Text #18

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1219. Min Act: -0.0002

Data Index: 1056014 (C4 (Web Text))

Max Activating Token Index: 36

Text #19

Max Range: 0.1813. Min Range: -0.1813

Max Act: 0.1208. Min Act: -0.0002

Data Index: 115784 (C4 (Web Text))

Max Activating Token Index: 98