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

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

Neuron 3191 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: 3.0727. Min Range: -3.0727

Max Act: 3.0727. Min Act: -0.0000

Data Index: 1442618 (Python Code)

Max Activating Token Index: 41

Text #1

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.7518. Min Act: -0.0000

Data Index: 1548338 (Python Code)

Max Activating Token Index: 54

Text #2

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.5878. Min Act: -0.0000

Data Index: 1518542 (Python Code)

Max Activating Token Index: 573

Text #3

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.7226. Min Act: -0.0000

Data Index: 1491964 (Python Code)

Max Activating Token Index: 548

Text #4

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.4018. Min Act: -0.0000

Data Index: 1364530 (Python Code)

Max Activating Token Index: 327

Text #5

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.5545. Min Act: -0.0000

Data Index: 1484748 (Python Code)

Max Activating Token Index: 261

Text #6

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.5665. Min Act: -0.0000

Data Index: 1505664 (Python Code)

Max Activating Token Index: 916

Text #7

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.4168. Min Act: -0.0000

Data Index: 1388384 (Python Code)

Max Activating Token Index: 808

Text #8

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.4065. Min Act: -0.0000

Data Index: 1587918 (Python Code)

Max Activating Token Index: 713

Text #9

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.5189. Min Act: -0.0000

Data Index: 1604376 (Python Code)

Max Activating Token Index: 771

Text #10

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.3996. Min Act: -0.0000

Data Index: 1633786 (Python Code)

Max Activating Token Index: 1006

Text #11

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.4805. Min Act: -0.0000

Data Index: 1456980 (Python Code)

Max Activating Token Index: 970

Text #12

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.5424. Min Act: -0.0000

Data Index: 1549207 (Python Code)

Max Activating Token Index: 234

Text #13

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.4109. Min Act: -0.0000

Data Index: 1506163 (Python Code)

Max Activating Token Index: 746

Text #14

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.5104. Min Act: -0.0000

Data Index: 1556513 (Python Code)

Max Activating Token Index: 36

Text #15

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.3794. Min Act: -0.0000

Data Index: 1368422 (Python Code)

Max Activating Token Index: 100

Text #16

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.3726. Min Act: -0.0000

Data Index: 1458823 (Python Code)

Max Activating Token Index: 463

Text #17

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.3820. Min Act: -0.0000

Data Index: 1618990 (Python Code)

Max Activating Token Index: 793

Text #18

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.0225. Min Act: -0.0000

Data Index: 1642649 (Python Code)

Max Activating Token Index: 861

Text #19

Max Range: 3.0727. Min Range: -3.0727

Max Act: 2.3583. Min Act: -0.0000

Data Index: 1369545 (Python Code)

Max Activating Token Index: 146