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

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

Neuron 3556 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8341. Min Act: -0.0000

Data Index: 1551862 (Python Code)

Max Activating Token Index: 799

Text #1

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.8703. Min Act: -0.0000

Data Index: 1551259 (Python Code)

Max Activating Token Index: 816

Text #2

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7764. Min Act: -0.0000

Data Index: 1628308 (Python Code)

Max Activating Token Index: 863

Text #3

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7554. Min Act: -0.0000

Data Index: 1513124 (Python Code)

Max Activating Token Index: 276

Text #4

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6555. Min Act: -0.0000

Data Index: 1435506 (Python Code)

Max Activating Token Index: 325

Text #5

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7015. Min Act: -0.0000

Data Index: 1414656 (Python Code)

Max Activating Token Index: 985

Text #6

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7461. Min Act: -0.0000

Data Index: 1512680 (Python Code)

Max Activating Token Index: 706

Text #7

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1644361 (Python Code)

Max Activating Token Index: 423

Text #8

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7170. Min Act: -0.0000

Data Index: 1462201 (Python Code)

Max Activating Token Index: 778

Text #9

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6971. Min Act: -0.0000

Data Index: 1470065 (Python Code)

Max Activating Token Index: 640

Text #10

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7142. Min Act: -0.0000

Data Index: 1515951 (Python Code)

Max Activating Token Index: 177

Text #11

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6601. Min Act: -0.0000

Data Index: 1442742 (Python Code)

Max Activating Token Index: 277

Text #12

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6962. Min Act: -0.0000

Data Index: 1550589 (Python Code)

Max Activating Token Index: 491

Text #13

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6544. Min Act: -0.0000

Data Index: 1469925 (Python Code)

Max Activating Token Index: 671

Text #14

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1555612 (Python Code)

Max Activating Token Index: 189

Text #15

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6861. Min Act: -0.0000

Data Index: 1456360 (Python Code)

Max Activating Token Index: 689

Text #16

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6818. Min Act: -0.0000

Data Index: 1449396 (Python Code)

Max Activating Token Index: 355

Text #17

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7303. Min Act: -0.0000

Data Index: 1484983 (Python Code)

Max Activating Token Index: 1020

Text #18

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.7028. Min Act: -0.0000

Data Index: 1518883 (Python Code)

Max Activating Token Index: 943

Text #19

Max Range: 0.8703. Min Range: -0.8703

Max Act: 0.6821. Min Act: -0.0000

Data Index: 1632822 (Python Code)

Max Activating Token Index: 397