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

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

Neuron 4648 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.6464. Min Act: -0.0000

Data Index: 1361096 (Python Code)

Max Activating Token Index: 943

Text #1

Max Range: 3.0663. Min Range: -3.0663

Max Act: 3.0663. Min Act: -0.0000

Data Index: 1562047 (Python Code)

Max Activating Token Index: 967

Text #2

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.7663. Min Act: -0.0000

Data Index: 1587899 (Python Code)

Max Activating Token Index: 324

Text #3

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.4902. Min Act: -0.0000

Data Index: 1586963 (Python Code)

Max Activating Token Index: 394

Text #4

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.7243. Min Act: -0.0000

Data Index: 1437706 (Python Code)

Max Activating Token Index: 1007

Text #5

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.4119. Min Act: -0.0000

Data Index: 1450165 (Python Code)

Max Activating Token Index: 1013

Text #6

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.3954. Min Act: -0.0000

Data Index: 1498721 (Python Code)

Max Activating Token Index: 918

Text #7

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.4562. Min Act: -0.0000

Data Index: 1490041 (Python Code)

Max Activating Token Index: 505

Text #8

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.5474. Min Act: -0.0000

Data Index: 1557172 (Python Code)

Max Activating Token Index: 360

Text #9

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.5054. Min Act: -0.0000

Data Index: 1533185 (Python Code)

Max Activating Token Index: 973

Text #10

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.3602. Min Act: -0.0000

Data Index: 1626906 (Python Code)

Max Activating Token Index: 960

Text #11

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.3251. Min Act: -0.0000

Data Index: 1459814 (Python Code)

Max Activating Token Index: 421

Text #12

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.2237. Min Act: -0.0000

Data Index: 1600372 (Python Code)

Max Activating Token Index: 649

Text #13

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.2955. Min Act: -0.0000

Data Index: 1486911 (Python Code)

Max Activating Token Index: 885

Text #14

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.0253. Min Act: -0.0000

Data Index: 1514461 (Python Code)

Max Activating Token Index: 65

Text #15

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.1270. Min Act: -0.0000

Data Index: 1564454 (Python Code)

Max Activating Token Index: 485

Text #16

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.1080. Min Act: -0.0000

Data Index: 380747 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.0010. Min Act: -0.0000

Data Index: 1469044 (Python Code)

Max Activating Token Index: 434

Text #18

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.0770. Min Act: -0.0000

Data Index: 1634758 (Python Code)

Max Activating Token Index: 738

Text #19

Max Range: 3.0663. Min Range: -3.0663

Max Act: 2.1993. Min Act: -0.0000

Data Index: 1590982 (Python Code)

Max Activating Token Index: 144