Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1309 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.0372. Min Range: -1.0372

Max Act: 1.0372. Min Act: -0.0000

Data Index: 1457292 (Python Code)

Max Activating Token Index: 972

Text #1

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.8570. Min Act: -0.0000

Data Index: 1380799 (Python Code)

Max Activating Token Index: 805

Text #2

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7625. Min Act: -0.0000

Data Index: 1589062 (Python Code)

Max Activating Token Index: 669

Text #3

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6785. Min Act: -0.0000

Data Index: 1588984 (Python Code)

Max Activating Token Index: 391

Text #4

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7787. Min Act: -0.0000

Data Index: 1485947 (Python Code)

Max Activating Token Index: 499

Text #5

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7798. Min Act: -0.0000

Data Index: 1513015 (Python Code)

Max Activating Token Index: 901

Text #6

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7628. Min Act: -0.0000

Data Index: 1398363 (Python Code)

Max Activating Token Index: 644

Text #7

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7472. Min Act: -0.0000

Data Index: 1381269 (Python Code)

Max Activating Token Index: 453

Text #8

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1459513 (Python Code)

Max Activating Token Index: 929

Text #9

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6946. Min Act: -0.0000

Data Index: 1398211 (Python Code)

Max Activating Token Index: 606

Text #10

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.7388. Min Act: -0.0000

Data Index: 1428949 (Python Code)

Max Activating Token Index: 421

Text #11

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6272. Min Act: -0.0000

Data Index: 1412961 (Python Code)

Max Activating Token Index: 255

Text #12

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6620. Min Act: -0.0000

Data Index: 1483122 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6209. Min Act: -0.0000

Data Index: 1628762 (Python Code)

Max Activating Token Index: 700

Text #14

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6291. Min Act: -0.0000

Data Index: 1418701 (Python Code)

Max Activating Token Index: 799

Text #15

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6027. Min Act: -0.0000

Data Index: 1535263 (Python Code)

Max Activating Token Index: 438

Text #16

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1614503 (Python Code)

Max Activating Token Index: 155

Text #17

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6604. Min Act: -0.0000

Data Index: 1605193 (Python Code)

Max Activating Token Index: 92

Text #18

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6414. Min Act: -0.0000

Data Index: 1542243 (Python Code)

Max Activating Token Index: 231

Text #19

Max Range: 1.0372. Min Range: -1.0372

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1434645 (Python Code)

Max Activating Token Index: 976