Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 965 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1793. Min Act: -0.0001

Data Index: 10053 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1661. Min Act: -0.0001

Data Index: 780374 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1618. Min Act: -0.0001

Data Index: 328285 (C4 (Web Text))

Max Activating Token Index: 532

Text #3

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1542. Min Act: -0.0001

Data Index: 269482 (C4 (Web Text))

Max Activating Token Index: 485

Text #4

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1476. Min Act: -0.0001

Data Index: 820669 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1191. Min Act: -0.0001

Data Index: 931735 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1331. Min Act: -0.0001

Data Index: 675059 (C4 (Web Text))

Max Activating Token Index: 731

Text #7

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1261. Min Act: -0.0001

Data Index: 279032 (C4 (Web Text))

Max Activating Token Index: 58

Text #8

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1353. Min Act: -0.0001

Data Index: 603097 (C4 (Web Text))

Max Activating Token Index: 788

Text #9

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1348. Min Act: -0.0001

Data Index: 1312464 (C4 (Web Text))

Max Activating Token Index: 219

Text #10

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1299. Min Act: -0.0001

Data Index: 1105430 (C4 (Web Text))

Max Activating Token Index: 305

Text #11

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1254. Min Act: -0.0001

Data Index: 758992 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1204. Min Act: -0.0001

Data Index: 1046146 (C4 (Web Text))

Max Activating Token Index: 459

Text #13

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1211. Min Act: -0.0001

Data Index: 319809 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1200. Min Act: -0.0001

Data Index: 1160634 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1239. Min Act: -0.0001

Data Index: 106448 (C4 (Web Text))

Max Activating Token Index: 263

Text #16

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1151. Min Act: -0.0001

Data Index: 118282 (C4 (Web Text))

Max Activating Token Index: 41

Text #17

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1220. Min Act: -0.0001

Data Index: 907235 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1215. Min Act: -0.0001

Data Index: 808445 (C4 (Web Text))

Max Activating Token Index: 123

Text #19

Max Range: 0.1793. Min Range: -0.1793

Max Act: 0.1255. Min Act: -0.0001

Data Index: 314213 (C4 (Web Text))

Max Activating Token Index: 52