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

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

Neuron 1963 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0405. Min Act: -0.0004

Data Index: 1635993 (Python Code)

Max Activating Token Index: 701

Text #1

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0366. Min Act: -0.0004

Data Index: 1572872 (Python Code)

Max Activating Token Index: 466

Text #2

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0361. Min Act: -0.0004

Data Index: 1627467 (Python Code)

Max Activating Token Index: 138

Text #3

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0353. Min Act: -0.0004

Data Index: 1392706 (Python Code)

Max Activating Token Index: 517

Text #4

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0324. Min Act: -0.0004

Data Index: 1516747 (Python Code)

Max Activating Token Index: 390

Text #5

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0331. Min Act: -0.0004

Data Index: 1565226 (Python Code)

Max Activating Token Index: 398

Text #6

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0336. Min Act: -0.0004

Data Index: 1370933 (Python Code)

Max Activating Token Index: 956

Text #7

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0328. Min Act: -0.0004

Data Index: 1520900 (Python Code)

Max Activating Token Index: 1015

Text #8

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0314. Min Act: -0.0004

Data Index: 1620273 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0346. Min Act: -0.0004

Data Index: 1608407 (Python Code)

Max Activating Token Index: 932

Text #10

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0323. Min Act: -0.0004

Data Index: 1507712 (Python Code)

Max Activating Token Index: 618

Text #11

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0317. Min Act: -0.0004

Data Index: 1508216 (Python Code)

Max Activating Token Index: 957

Text #12

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0322. Min Act: -0.0004

Data Index: 1405352 (Python Code)

Max Activating Token Index: 43

Text #13

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0281. Min Act: -0.0004

Data Index: 1497443 (Python Code)

Max Activating Token Index: 208

Text #14

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0318. Min Act: -0.0004

Data Index: 1622318 (Python Code)

Max Activating Token Index: 262

Text #15

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0299. Min Act: -0.0004

Data Index: 1402384 (Python Code)

Max Activating Token Index: 318

Text #16

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0308. Min Act: -0.0004

Data Index: 1640511 (Python Code)

Max Activating Token Index: 303

Text #17

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0305. Min Act: -0.0004

Data Index: 1643806 (Python Code)

Max Activating Token Index: 258

Text #18

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0283. Min Act: -0.0004

Data Index: 1492941 (Python Code)

Max Activating Token Index: 268

Text #19

Max Range: 0.0405. Min Range: -0.0405

Max Act: 0.0280. Min Act: -0.0004

Data Index: 1555272 (Python Code)

Max Activating Token Index: 150