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

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

Neuron 2559 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.2178. Min Act: -0.0000

Data Index: 113792 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0464. Min Act: -0.0000

Data Index: 304581 (C4 (Web Text))

Max Activating Token Index: 288

Text #2

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.2097. Min Act: -0.0000

Data Index: 953929 (C4 (Web Text))

Max Activating Token Index: 423

Text #3

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.1100. Min Act: -0.0000

Data Index: 311109 (C4 (Web Text))

Max Activating Token Index: 382

Text #4

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.1316. Min Act: -0.0000

Data Index: 125510 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.1346. Min Act: -0.0000

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 180

Text #6

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0539. Min Act: -0.0000

Data Index: 1072257 (C4 (Web Text))

Max Activating Token Index: 150

Text #7

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.2187. Min Act: -0.0000

Data Index: 774393 (C4 (Web Text))

Max Activating Token Index: 258

Text #8

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0592. Min Act: -0.0000

Data Index: 748077 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 1.2187. Min Range: -1.2187

Max Act: 1.0545. Min Act: -0.0000

Data Index: 87069 (C4 (Web Text))

Max Activating Token Index: 965

Text #10

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.9640. Min Act: -0.0000

Data Index: 264739 (C4 (Web Text))

Max Activating Token Index: 265

Text #11

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8323. Min Act: -0.0000

Data Index: 1088243 (C4 (Web Text))

Max Activating Token Index: 653

Text #12

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8421. Min Act: -0.0000

Data Index: 362023 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8224. Min Act: -0.0000

Data Index: 1032177 (C4 (Web Text))

Max Activating Token Index: 906

Text #14

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1212119 (C4 (Web Text))

Max Activating Token Index: 219

Text #15

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.7240. Min Act: -0.0000

Data Index: 1120498 (C4 (Web Text))

Max Activating Token Index: 603

Text #16

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.8233. Min Act: -0.0000

Data Index: 487002 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1620518 (Python Code)

Max Activating Token Index: 287

Text #18

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.7902. Min Act: -0.0000

Data Index: 351244 (C4 (Web Text))

Max Activating Token Index: 147

Text #19

Max Range: 1.2187. Min Range: -1.2187

Max Act: 0.7515. Min Act: -0.0000

Data Index: 1208992 (C4 (Web Text))

Max Activating Token Index: 126