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

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

Neuron 2774 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2464. Min Act: -0.0000

Data Index: 1423041 (Python Code)

Max Activating Token Index: 47

Text #1

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2342. Min Act: -0.0000

Data Index: 425865 (C4 (Web Text))

Max Activating Token Index: 656

Text #2

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2561. Min Act: -0.0000

Data Index: 955610 (C4 (Web Text))

Max Activating Token Index: 657

Text #3

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2447. Min Act: -0.0000

Data Index: 138035 (C4 (Web Text))

Max Activating Token Index: 228

Text #4

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2380. Min Act: -0.0000

Data Index: 1579227 (Python Code)

Max Activating Token Index: 901

Text #5

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2379. Min Act: -0.0000

Data Index: 1450860 (Python Code)

Max Activating Token Index: 274

Text #6

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2314. Min Act: -0.0000

Data Index: 1526672 (Python Code)

Max Activating Token Index: 271

Text #7

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2466. Min Act: -0.0000

Data Index: 1434554 (Python Code)

Max Activating Token Index: 425

Text #8

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2372. Min Act: -0.0000

Data Index: 1396205 (Python Code)

Max Activating Token Index: 610

Text #9

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2342. Min Act: -0.0000

Data Index: 1458382 (Python Code)

Max Activating Token Index: 592

Text #10

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2343. Min Act: -0.0000

Data Index: 1496137 (Python Code)

Max Activating Token Index: 232

Text #11

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2243. Min Act: -0.0000

Data Index: 1581852 (Python Code)

Max Activating Token Index: 330

Text #12

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2315. Min Act: -0.0000

Data Index: 24759 (C4 (Web Text))

Max Activating Token Index: 480

Text #13

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2310. Min Act: -0.0000

Data Index: 1399552 (Python Code)

Max Activating Token Index: 770

Text #14

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2298. Min Act: -0.0000

Data Index: 853297 (C4 (Web Text))

Max Activating Token Index: 312

Text #15

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2373. Min Act: -0.0000

Data Index: 1403571 (Python Code)

Max Activating Token Index: 973

Text #16

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2333. Min Act: -0.0000

Data Index: 1516174 (Python Code)

Max Activating Token Index: 179

Text #17

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2176. Min Act: -0.0000

Data Index: 1457185 (Python Code)

Max Activating Token Index: 787

Text #18

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2297. Min Act: -0.0000

Data Index: 265892 (C4 (Web Text))

Max Activating Token Index: 280

Text #19

Max Range: 0.2561. Min Range: -0.2561

Max Act: 0.2157. Min Act: -0.0000

Data Index: 1583877 (Python Code)

Max Activating Token Index: 563