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

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

Neuron 3865 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.1802. Min Act: -0.0000

Data Index: 1618978 (Python Code)

Max Activating Token Index: 151

Text #1

Max Range: 1.1802. Min Range: -1.1802

Max Act: 1.0659. Min Act: -0.0000

Data Index: 1463616 (Python Code)

Max Activating Token Index: 866

Text #2

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.9428. Min Act: -0.0000

Data Index: 1560758 (Python Code)

Max Activating Token Index: 771

Text #3

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.9854. Min Act: -0.0000

Data Index: 1450029 (Python Code)

Max Activating Token Index: 690

Text #4

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8132. Min Act: -0.0000

Data Index: 1500655 (Python Code)

Max Activating Token Index: 983

Text #5

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8603. Min Act: -0.0000

Data Index: 1457550 (Python Code)

Max Activating Token Index: 701

Text #6

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.9010. Min Act: -0.0000

Data Index: 1464710 (Python Code)

Max Activating Token Index: 204

Text #7

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.9016. Min Act: -0.0000

Data Index: 1585752 (Python Code)

Max Activating Token Index: 746

Text #8

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8214. Min Act: -0.0000

Data Index: 1608021 (Python Code)

Max Activating Token Index: 737

Text #9

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8736. Min Act: -0.0000

Data Index: 1362701 (Python Code)

Max Activating Token Index: 473

Text #10

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8144. Min Act: -0.0000

Data Index: 1503869 (Python Code)

Max Activating Token Index: 507

Text #11

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.8153. Min Act: -0.0000

Data Index: 1592348 (Python Code)

Max Activating Token Index: 365

Text #12

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7498. Min Act: -0.0000

Data Index: 1440706 (Python Code)

Max Activating Token Index: 823

Text #13

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1618576 (Python Code)

Max Activating Token Index: 437

Text #14

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7424. Min Act: -0.0000

Data Index: 1559637 (Python Code)

Max Activating Token Index: 143

Text #15

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1571016 (Python Code)

Max Activating Token Index: 753

Text #16

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1654697 (Python Code)

Max Activating Token Index: 989

Text #17

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7566. Min Act: -0.0000

Data Index: 1399615 (Python Code)

Max Activating Token Index: 264

Text #18

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7067. Min Act: -0.0000

Data Index: 1501071 (Python Code)

Max Activating Token Index: 820

Text #19

Max Range: 1.1802. Min Range: -1.1802

Max Act: 0.7931. Min Act: -0.0000

Data Index: 1565346 (Python Code)

Max Activating Token Index: 711