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

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

Neuron 4545 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.0964. Min Range: -5.0964

Max Act: 5.0964. Min Act: -0.0000

Data Index: 1589664 (Python Code)

Max Activating Token Index: 55

Text #1

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.8422. Min Act: -0.0000

Data Index: 1640428 (Python Code)

Max Activating Token Index: 942

Text #2

Max Range: 5.0964. Min Range: -5.0964

Max Act: 5.0000. Min Act: -0.0000

Data Index: 1588545 (Python Code)

Max Activating Token Index: 346

Text #3

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.9633. Min Act: -0.0000

Data Index: 352521 (C4 (Web Text))

Max Activating Token Index: 563

Text #4

Max Range: 5.0964. Min Range: -5.0964

Max Act: 5.0861. Min Act: -0.0000

Data Index: 1603809 (Python Code)

Max Activating Token Index: 661

Text #5

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.9124. Min Act: -0.0000

Data Index: 173327 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.6975. Min Act: -0.0000

Data Index: 1373679 (Python Code)

Max Activating Token Index: 80

Text #7

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.8210. Min Act: -0.0000

Data Index: 1646642 (Python Code)

Max Activating Token Index: 713

Text #8

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.5995. Min Act: -0.0000

Data Index: 1521102 (Python Code)

Max Activating Token Index: 287

Text #9

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.5279. Min Act: -0.0000

Data Index: 1406784 (Python Code)

Max Activating Token Index: 387

Text #10

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.4930. Min Act: -0.0000

Data Index: 1545605 (Python Code)

Max Activating Token Index: 115

Text #11

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.4681. Min Act: -0.0000

Data Index: 1383093 (Python Code)

Max Activating Token Index: 364

Text #12

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.7659. Min Act: -0.0000

Data Index: 1361648 (Python Code)

Max Activating Token Index: 911

Text #13

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.5463. Min Act: -0.0000

Data Index: 1359897 (Python Code)

Max Activating Token Index: 544

Text #14

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.1624. Min Act: -0.0000

Data Index: 1395872 (Python Code)

Max Activating Token Index: 395

Text #15

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.1026. Min Act: -0.0000

Data Index: 1568469 (Python Code)

Max Activating Token Index: 886

Text #16

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.4247. Min Act: -0.0000

Data Index: 1370529 (Python Code)

Max Activating Token Index: 324

Text #17

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.3782. Min Act: -0.0000

Data Index: 1442718 (Python Code)

Max Activating Token Index: 365

Text #18

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.1647. Min Act: -0.0000

Data Index: 1432790 (Python Code)

Max Activating Token Index: 360

Text #19

Max Range: 5.0964. Min Range: -5.0964

Max Act: 4.3139. Min Act: -0.0000

Data Index: 1582303 (Python Code)

Max Activating Token Index: 483