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

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

Neuron 3957 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1417. Min Act: -0.0001

Data Index: 657991 (C4 (Web Text))

Max Activating Token Index: 796

Text #1

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1354. Min Act: -0.0000

Data Index: 1299235 (C4 (Web Text))

Max Activating Token Index: 385

Text #2

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1350. Min Act: -0.0001

Data Index: 1435487 (Python Code)

Max Activating Token Index: 222

Text #3

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1351. Min Act: -0.0000

Data Index: 1447973 (Python Code)

Max Activating Token Index: 195

Text #4

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1306. Min Act: -0.0000

Data Index: 1619845 (Python Code)

Max Activating Token Index: 420

Text #5

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1491060 (Python Code)

Max Activating Token Index: 333

Text #6

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1365. Min Act: -0.0001

Data Index: 1409326 (Python Code)

Max Activating Token Index: 884

Text #7

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1179. Min Act: -0.0001

Data Index: 73178 (C4 (Web Text))

Max Activating Token Index: 181

Text #8

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1277. Min Act: -0.0001

Data Index: 1574497 (Python Code)

Max Activating Token Index: 520

Text #9

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1276. Min Act: -0.0000

Data Index: 1639810 (Python Code)

Max Activating Token Index: 508

Text #10

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1217. Min Act: -0.0001

Data Index: 636349 (C4 (Web Text))

Max Activating Token Index: 662

Text #11

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1303. Min Act: -0.0001

Data Index: 1610324 (Python Code)

Max Activating Token Index: 311

Text #12

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1252. Min Act: -0.0001

Data Index: 1405435 (Python Code)

Max Activating Token Index: 625

Text #13

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1130. Min Act: -0.0001

Data Index: 461626 (C4 (Web Text))

Max Activating Token Index: 586

Text #14

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1087. Min Act: -0.0001

Data Index: 1550081 (Python Code)

Max Activating Token Index: 258

Text #15

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1134. Min Act: -0.0000

Data Index: 1456152 (Python Code)

Max Activating Token Index: 553

Text #16

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1125. Min Act: -0.0001

Data Index: 1604165 (Python Code)

Max Activating Token Index: 898

Text #17

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1156. Min Act: -0.0000

Data Index: 1463627 (Python Code)

Max Activating Token Index: 429

Text #18

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1106. Min Act: -0.0001

Data Index: 1446179 (Python Code)

Max Activating Token Index: 668

Text #19

Max Range: 0.1417. Min Range: -0.1417

Max Act: 0.1129. Min Act: -0.0001

Data Index: 1593785 (Python Code)

Max Activating Token Index: 235