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

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

Neuron 3306 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3143. Min Range: -1.3143

Max Act: 1.3143. Min Act: -0.0000

Data Index: 1612006 (Python Code)

Max Activating Token Index: 354

Text #1

Max Range: 1.3143. Min Range: -1.3143

Max Act: 1.1509. Min Act: -0.0000

Data Index: 1568741 (Python Code)

Max Activating Token Index: 540

Text #2

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8494. Min Act: -0.0000

Data Index: 1442940 (Python Code)

Max Activating Token Index: 613

Text #3

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.9026. Min Act: -0.0000

Data Index: 1381419 (Python Code)

Max Activating Token Index: 685

Text #4

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8632. Min Act: -0.0000

Data Index: 1519297 (Python Code)

Max Activating Token Index: 896

Text #5

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8807. Min Act: -0.0000

Data Index: 1460294 (Python Code)

Max Activating Token Index: 488

Text #6

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1499407 (Python Code)

Max Activating Token Index: 897

Text #7

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8729. Min Act: -0.0000

Data Index: 1639693 (Python Code)

Max Activating Token Index: 581

Text #8

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8019. Min Act: -0.0000

Data Index: 1477527 (Python Code)

Max Activating Token Index: 879

Text #9

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.8108. Min Act: -0.0000

Data Index: 1439700 (Python Code)

Max Activating Token Index: 773

Text #10

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7944. Min Act: -0.0000

Data Index: 1499262 (Python Code)

Max Activating Token Index: 351

Text #11

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7786. Min Act: -0.0000

Data Index: 1372289 (Python Code)

Max Activating Token Index: 590

Text #12

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7439. Min Act: -0.0000

Data Index: 1563398 (Python Code)

Max Activating Token Index: 230

Text #13

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7508. Min Act: -0.0000

Data Index: 1457204 (Python Code)

Max Activating Token Index: 431

Text #14

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7678. Min Act: -0.0000

Data Index: 1377924 (Python Code)

Max Activating Token Index: 456

Text #15

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7683. Min Act: -0.0000

Data Index: 1619077 (Python Code)

Max Activating Token Index: 974

Text #16

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7397. Min Act: -0.0000

Data Index: 1472598 (Python Code)

Max Activating Token Index: 409

Text #17

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7248. Min Act: -0.0000

Data Index: 1433137 (Python Code)

Max Activating Token Index: 757

Text #18

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1469473 (Python Code)

Max Activating Token Index: 715

Text #19

Max Range: 1.3143. Min Range: -1.3143

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1629125 (Python Code)

Max Activating Token Index: 924