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

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

Neuron 2804 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.3341. Min Act: -0.0000

Data Index: 1101843 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1308. Min Act: -0.0000

Data Index: 1087995 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1711. Min Act: -0.0000

Data Index: 337427 (C4 (Web Text))

Max Activating Token Index: 142

Text #3

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1879. Min Act: -0.0000

Data Index: 56948 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.1057. Min Act: -0.0000

Data Index: 1048250 (C4 (Web Text))

Max Activating Token Index: 40

Text #5

Max Range: 1.3341. Min Range: -1.3341

Max Act: 1.0101. Min Act: -0.0000

Data Index: 248921 (C4 (Web Text))

Max Activating Token Index: 108

Text #6

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9976. Min Act: -0.0000

Data Index: 858751 (C4 (Web Text))

Max Activating Token Index: 791

Text #7

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9917. Min Act: -0.0000

Data Index: 294785 (C4 (Web Text))

Max Activating Token Index: 448

Text #8

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9493. Min Act: -0.0000

Data Index: 94605 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.8852. Min Act: -0.0000

Data Index: 849439 (C4 (Web Text))

Max Activating Token Index: 496

Text #10

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9336. Min Act: -0.0000

Data Index: 151530 (C4 (Web Text))

Max Activating Token Index: 934

Text #11

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9804. Min Act: -0.0000

Data Index: 354447 (C4 (Web Text))

Max Activating Token Index: 876

Text #12

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9219. Min Act: -0.0000

Data Index: 905250 (C4 (Web Text))

Max Activating Token Index: 956

Text #13

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9771. Min Act: -0.0000

Data Index: 1232275 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9030. Min Act: -0.0000

Data Index: 862261 (C4 (Web Text))

Max Activating Token Index: 1013

Text #15

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9004. Min Act: -0.0000

Data Index: 1282383 (C4 (Web Text))

Max Activating Token Index: 646

Text #16

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.9027. Min Act: -0.0000

Data Index: 338 (C4 (Web Text))

Max Activating Token Index: 748

Text #17

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.8306. Min Act: -0.0000

Data Index: 857729 (C4 (Web Text))

Max Activating Token Index: 712

Text #18

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.8719. Min Act: -0.0000

Data Index: 675810 (C4 (Web Text))

Max Activating Token Index: 390

Text #19

Max Range: 1.3341. Min Range: -1.3341

Max Act: 0.8649. Min Act: -0.0000

Data Index: 1089478 (C4 (Web Text))

Max Activating Token Index: 419