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

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

Neuron 2375 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: 1.4777. Min Range: -1.4777

Max Act: 1.4777. Min Act: -0.0000

Data Index: 1329808 (C4 (Web Text))

Max Activating Token Index: 735

Text #1

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.3254. Min Act: -0.0000

Data Index: 728698 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.2573. Min Act: -0.0000

Data Index: 700795 (C4 (Web Text))

Max Activating Token Index: 727

Text #3

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.3694. Min Act: -0.0000

Data Index: 213273 (C4 (Web Text))

Max Activating Token Index: 688

Text #4

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1199. Min Act: -0.0000

Data Index: 1212506 (C4 (Web Text))

Max Activating Token Index: 1012

Text #5

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.2539. Min Act: -0.0000

Data Index: 895932 (C4 (Web Text))

Max Activating Token Index: 554

Text #6

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.2778. Min Act: -0.0000

Data Index: 720351 (C4 (Web Text))

Max Activating Token Index: 214

Text #7

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1923. Min Act: -0.0000

Data Index: 851772 (C4 (Web Text))

Max Activating Token Index: 572

Text #8

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.3077. Min Act: -0.0000

Data Index: 455108 (C4 (Web Text))

Max Activating Token Index: 629

Text #9

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1771. Min Act: -0.0000

Data Index: 1423285 (Python Code)

Max Activating Token Index: 369

Text #10

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1781. Min Act: -0.0000

Data Index: 1014916 (C4 (Web Text))

Max Activating Token Index: 92

Text #11

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1411. Min Act: -0.0000

Data Index: 1209237 (C4 (Web Text))

Max Activating Token Index: 742

Text #12

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1098. Min Act: -0.0000

Data Index: 1380259 (Python Code)

Max Activating Token Index: 976

Text #13

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1051. Min Act: -0.0000

Data Index: 1500141 (Python Code)

Max Activating Token Index: 900

Text #14

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.2003. Min Act: -0.0000

Data Index: 617556 (C4 (Web Text))

Max Activating Token Index: 888

Text #15

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1701. Min Act: -0.0000

Data Index: 947883 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1224. Min Act: -0.0000

Data Index: 139013 (C4 (Web Text))

Max Activating Token Index: 581

Text #17

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.0960. Min Act: -0.0000

Data Index: 1446373 (Python Code)

Max Activating Token Index: 1008

Text #18

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1143327 (C4 (Web Text))

Max Activating Token Index: 429

Text #19

Max Range: 1.4777. Min Range: -1.4777

Max Act: 1.1183. Min Act: -0.0000

Data Index: 1259557 (C4 (Web Text))

Max Activating Token Index: 874