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

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

Neuron 1347 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: 3.6200. Min Range: -3.6200

Max Act: 3.5384. Min Act: -0.0000

Data Index: 300840 (C4 (Web Text))

Max Activating Token Index: 327

Text #1

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.6200. Min Act: -0.0000

Data Index: 1139738 (C4 (Web Text))

Max Activating Token Index: 48

Text #2

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.4743. Min Act: -0.0000

Data Index: 784854 (C4 (Web Text))

Max Activating Token Index: 476

Text #3

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.5310. Min Act: -0.0000

Data Index: 1071147 (C4 (Web Text))

Max Activating Token Index: 7

Text #4

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.1847. Min Act: -0.0000

Data Index: 488175 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.2183. Min Act: -0.0000

Data Index: 863546 (C4 (Web Text))

Max Activating Token Index: 935

Text #6

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.0524. Min Act: -0.0000

Data Index: 339009 (C4 (Web Text))

Max Activating Token Index: 657

Text #7

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.0109. Min Act: -0.0000

Data Index: 1474806 (Python Code)

Max Activating Token Index: 112

Text #8

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.9958. Min Act: -0.0000

Data Index: 888969 (C4 (Web Text))

Max Activating Token Index: 243

Text #9

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.7926. Min Act: -0.0000

Data Index: 1190692 (C4 (Web Text))

Max Activating Token Index: 767

Text #10

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.8891. Min Act: -0.0000

Data Index: 740287 (C4 (Web Text))

Max Activating Token Index: 81

Text #11

Max Range: 3.6200. Min Range: -3.6200

Max Act: 3.0175. Min Act: -0.0000

Data Index: 233911 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.7805. Min Act: -0.0000

Data Index: 1025368 (C4 (Web Text))

Max Activating Token Index: 569

Text #13

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.9058. Min Act: -0.0000

Data Index: 1430735 (Python Code)

Max Activating Token Index: 985

Text #14

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.7490. Min Act: -0.0000

Data Index: 1280585 (C4 (Web Text))

Max Activating Token Index: 130

Text #15

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.8734. Min Act: -0.0000

Data Index: 62470 (C4 (Web Text))

Max Activating Token Index: 110

Text #16

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.7269. Min Act: -0.0000

Data Index: 376839 (C4 (Web Text))

Max Activating Token Index: 62

Text #17

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.7082. Min Act: -0.0000

Data Index: 977340 (C4 (Web Text))

Max Activating Token Index: 265

Text #18

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.7001. Min Act: -0.0000

Data Index: 1069981 (C4 (Web Text))

Max Activating Token Index: 16

Text #19

Max Range: 3.6200. Min Range: -3.6200

Max Act: 2.8182. Min Act: -0.0000

Data Index: 220034 (C4 (Web Text))

Max Activating Token Index: 20