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

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

Neuron 3377 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1516. Min Act: -0.0000

Data Index: 707237 (C4 (Web Text))

Max Activating Token Index: 389

Text #1

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1491. Min Act: -0.0000

Data Index: 1135762 (C4 (Web Text))

Max Activating Token Index: 700

Text #2

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1377. Min Act: -0.0000

Data Index: 749211 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1386. Min Act: -0.0000

Data Index: 998623 (C4 (Web Text))

Max Activating Token Index: 515

Text #4

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1427. Min Act: -0.0000

Data Index: 1147530 (C4 (Web Text))

Max Activating Token Index: 955

Text #5

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1347. Min Act: -0.0000

Data Index: 225533 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1359. Min Act: -0.0000

Data Index: 602989 (C4 (Web Text))

Max Activating Token Index: 429

Text #7

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1243. Min Act: -0.0000

Data Index: 1046851 (C4 (Web Text))

Max Activating Token Index: 782

Text #8

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1336. Min Act: -0.0000

Data Index: 15019 (C4 (Web Text))

Max Activating Token Index: 332

Text #9

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1242. Min Act: -0.0000

Data Index: 348581 (C4 (Web Text))

Max Activating Token Index: 959

Text #10

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1383. Min Act: -0.0000

Data Index: 589 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1226. Min Act: -0.0000

Data Index: 809726 (C4 (Web Text))

Max Activating Token Index: 68

Text #12

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1180. Min Act: -0.0000

Data Index: 1351573 (C4 (Web Text))

Max Activating Token Index: 461

Text #13

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1204. Min Act: -0.0000

Data Index: 525547 (C4 (Web Text))

Max Activating Token Index: 396

Text #14

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1113. Min Act: -0.0000

Data Index: 490558 (C4 (Web Text))

Max Activating Token Index: 776

Text #15

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1221. Min Act: -0.0000

Data Index: 829964 (C4 (Web Text))

Max Activating Token Index: 704

Text #16

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1125. Min Act: -0.0001

Data Index: 428446 (C4 (Web Text))

Max Activating Token Index: 388

Text #17

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1162. Min Act: -0.0000

Data Index: 752645 (C4 (Web Text))

Max Activating Token Index: 491

Text #18

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1156. Min Act: -0.0000

Data Index: 262530 (C4 (Web Text))

Max Activating Token Index: 669

Text #19

Max Range: 0.1516. Min Range: -0.1516

Max Act: 0.1149. Min Act: -0.0000

Data Index: 432781 (C4 (Web Text))

Max Activating Token Index: 165