Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3303 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.7173. Min Act: -0.0000

Data Index: 770462 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6956. Min Act: -0.0000

Data Index: 1181406 (C4 (Web Text))

Max Activating Token Index: 186

Text #2

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6611. Min Act: -0.0000

Data Index: 935374 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6882. Min Act: -0.0000

Data Index: 1159505 (C4 (Web Text))

Max Activating Token Index: 195

Text #4

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6391. Min Act: -0.0000

Data Index: 99557 (C4 (Web Text))

Max Activating Token Index: 665

Text #5

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6326. Min Act: -0.0000

Data Index: 1195589 (C4 (Web Text))

Max Activating Token Index: 498

Text #6

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6274. Min Act: -0.0000

Data Index: 885261 (C4 (Web Text))

Max Activating Token Index: 124

Text #7

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6209. Min Act: -0.0000

Data Index: 660856 (C4 (Web Text))

Max Activating Token Index: 643

Text #8

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6432. Min Act: 0.0000

Data Index: 102597 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.6034. Min Act: -0.0000

Data Index: 781281 (C4 (Web Text))

Max Activating Token Index: 250

Text #10

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5809. Min Act: -0.0000

Data Index: 71414 (C4 (Web Text))

Max Activating Token Index: 557

Text #11

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5536. Min Act: -0.0000

Data Index: 831905 (C4 (Web Text))

Max Activating Token Index: 478

Text #12

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5687. Min Act: -0.0000

Data Index: 907080 (C4 (Web Text))

Max Activating Token Index: 533

Text #13

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5658. Min Act: 0.0000

Data Index: 221688 (C4 (Web Text))

Max Activating Token Index: 219

Text #14

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5541. Min Act: -0.0000

Data Index: 1110004 (C4 (Web Text))

Max Activating Token Index: 933

Text #15

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5335. Min Act: -0.0000

Data Index: 995535 (C4 (Web Text))

Max Activating Token Index: 360

Text #16

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5007. Min Act: -0.0000

Data Index: 115520 (C4 (Web Text))

Max Activating Token Index: 884

Text #17

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5121. Min Act: -0.0000

Data Index: 466673 (C4 (Web Text))

Max Activating Token Index: 1005

Text #18

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5397. Min Act: -0.0000

Data Index: 345099 (C4 (Web Text))

Max Activating Token Index: 943

Text #19

Max Range: 0.7173. Min Range: -0.7173

Max Act: 0.5107. Min Act: 0.0000

Data Index: 417834 (C4 (Web Text))

Max Activating Token Index: 226