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

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

Neuron 4819 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: 5.8096. Min Range: -5.8096

Max Act: 5.8096. Min Act: -0.0000

Data Index: 1426244 (Python Code)

Max Activating Token Index: 573

Text #1

Max Range: 5.8096. Min Range: -5.8096

Max Act: 5.3101. Min Act: -0.0000

Data Index: 1505620 (Python Code)

Max Activating Token Index: 102

Text #2

Max Range: 5.8096. Min Range: -5.8096

Max Act: 5.2327. Min Act: -0.0000

Data Index: 1550207 (Python Code)

Max Activating Token Index: 119

Text #3

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.9219. Min Act: -0.0000

Data Index: 1539645 (Python Code)

Max Activating Token Index: 555

Text #4

Max Range: 5.8096. Min Range: -5.8096

Max Act: 5.1004. Min Act: -0.0000

Data Index: 1479877 (Python Code)

Max Activating Token Index: 801

Text #5

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.7948. Min Act: -0.0000

Data Index: 1647601 (Python Code)

Max Activating Token Index: 945

Text #6

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.9747. Min Act: -0.0000

Data Index: 1506462 (Python Code)

Max Activating Token Index: 640

Text #7

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.9319. Min Act: -0.0000

Data Index: 1402339 (Python Code)

Max Activating Token Index: 829

Text #8

Max Range: 5.8096. Min Range: -5.8096

Max Act: 5.1017. Min Act: -0.0000

Data Index: 1623427 (Python Code)

Max Activating Token Index: 390

Text #9

Max Range: 5.8096. Min Range: -5.8096

Max Act: 5.1041. Min Act: -0.0000

Data Index: 1607263 (Python Code)

Max Activating Token Index: 24

Text #10

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.6845. Min Act: -0.0000

Data Index: 1470865 (Python Code)

Max Activating Token Index: 312

Text #11

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.5341. Min Act: -0.0000

Data Index: 1396315 (Python Code)

Max Activating Token Index: 664

Text #12

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.5299. Min Act: -0.0000

Data Index: 1568813 (Python Code)

Max Activating Token Index: 743

Text #13

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.5314. Min Act: -0.0000

Data Index: 1465958 (Python Code)

Max Activating Token Index: 907

Text #14

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.4838. Min Act: -0.0000

Data Index: 1470862 (Python Code)

Max Activating Token Index: 643

Text #15

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.6372. Min Act: -0.0000

Data Index: 1479732 (Python Code)

Max Activating Token Index: 376

Text #16

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.3901. Min Act: -0.0000

Data Index: 1644014 (Python Code)

Max Activating Token Index: 617

Text #17

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.7984. Min Act: -0.0000

Data Index: 1566833 (Python Code)

Max Activating Token Index: 275

Text #18

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.2664. Min Act: -0.0000

Data Index: 1380225 (Python Code)

Max Activating Token Index: 358

Text #19

Max Range: 5.8096. Min Range: -5.8096

Max Act: 4.5856. Min Act: -0.0000

Data Index: 1586027 (Python Code)

Max Activating Token Index: 892