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

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

Neuron 2508 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.9560. Min Act: -0.0000

Data Index: 1493699 (Python Code)

Max Activating Token Index: 306

Text #1

Max Range: 1.0373. Min Range: -1.0373

Max Act: 1.0373. Min Act: -0.0000

Data Index: 1375219 (Python Code)

Max Activating Token Index: 749

Text #2

Max Range: 1.0373. Min Range: -1.0373

Max Act: 1.0115. Min Act: -0.0000

Data Index: 1394539 (Python Code)

Max Activating Token Index: 262

Text #3

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.9282. Min Act: -0.0000

Data Index: 1381190 (Python Code)

Max Activating Token Index: 542

Text #4

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.8383. Min Act: -0.0000

Data Index: 1626500 (Python Code)

Max Activating Token Index: 699

Text #5

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.8644. Min Act: -0.0000

Data Index: 1610594 (Python Code)

Max Activating Token Index: 219

Text #6

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.9221. Min Act: -0.0000

Data Index: 1254377 (C4 (Web Text))

Max Activating Token Index: 733

Text #7

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.9458. Min Act: -0.0000

Data Index: 1475782 (Python Code)

Max Activating Token Index: 653

Text #8

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.8220. Min Act: -0.0000

Data Index: 1498919 (Python Code)

Max Activating Token Index: 277

Text #9

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.9002. Min Act: -0.0000

Data Index: 1463271 (Python Code)

Max Activating Token Index: 446

Text #10

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.8117. Min Act: -0.0000

Data Index: 1535954 (Python Code)

Max Activating Token Index: 777

Text #11

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1385163 (Python Code)

Max Activating Token Index: 589

Text #12

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.7996. Min Act: -0.0000

Data Index: 1551139 (Python Code)

Max Activating Token Index: 766

Text #13

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.7365. Min Act: -0.0000

Data Index: 1523885 (Python Code)

Max Activating Token Index: 212

Text #14

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.7507. Min Act: -0.0000

Data Index: 1574482 (Python Code)

Max Activating Token Index: 407

Text #15

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.7227. Min Act: -0.0000

Data Index: 1544543 (Python Code)

Max Activating Token Index: 747

Text #16

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.7715. Min Act: -0.0000

Data Index: 473629 (C4 (Web Text))

Max Activating Token Index: 716

Text #17

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.7850. Min Act: -0.0000

Data Index: 1382825 (Python Code)

Max Activating Token Index: 251

Text #18

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.7493. Min Act: -0.0000

Data Index: 1614424 (Python Code)

Max Activating Token Index: 329

Text #19

Max Range: 1.0373. Min Range: -1.0373

Max Act: 0.6970. Min Act: -0.0000

Data Index: 1485573 (Python Code)

Max Activating Token Index: 526