Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1521 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1052. Min Act: -0.0001

Data Index: 681346 (C4 (Web Text))

Max Activating Token Index: 621

Text #1

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1049. Min Act: -0.0001

Data Index: 13984 (C4 (Web Text))

Max Activating Token Index: 280

Text #2

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1035. Min Act: -0.0001

Data Index: 354430 (C4 (Web Text))

Max Activating Token Index: 538

Text #3

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.1006. Min Act: -0.0001

Data Index: 1211101 (C4 (Web Text))

Max Activating Token Index: 70

Text #4

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0976. Min Act: -0.0001

Data Index: 1357514 (C4 (Web Text))

Max Activating Token Index: 715

Text #5

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0945. Min Act: -0.0001

Data Index: 491063 (C4 (Web Text))

Max Activating Token Index: 1001

Text #6

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0912. Min Act: -0.0000

Data Index: 1002303 (C4 (Web Text))

Max Activating Token Index: 645

Text #7

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0895. Min Act: -0.0001

Data Index: 1589249 (Python Code)

Max Activating Token Index: 451

Text #8

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1047645 (C4 (Web Text))

Max Activating Token Index: 574

Text #9

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1059199 (C4 (Web Text))

Max Activating Token Index: 122

Text #10

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0867. Min Act: -0.0001

Data Index: 587725 (C4 (Web Text))

Max Activating Token Index: 859

Text #11

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0867. Min Act: -0.0001

Data Index: 181638 (C4 (Web Text))

Max Activating Token Index: 89

Text #12

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0851. Min Act: -0.0001

Data Index: 1256035 (C4 (Web Text))

Max Activating Token Index: 90

Text #13

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0881. Min Act: -0.0001

Data Index: 989352 (C4 (Web Text))

Max Activating Token Index: 626

Text #14

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0877. Min Act: -0.0001

Data Index: 1278202 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0853. Min Act: -0.0001

Data Index: 1374512 (Python Code)

Max Activating Token Index: 535

Text #16

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0852. Min Act: -0.0001

Data Index: 1471991 (Python Code)

Max Activating Token Index: 486

Text #17

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0768. Min Act: -0.0001

Data Index: 452875 (C4 (Web Text))

Max Activating Token Index: 326

Text #18

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0876. Min Act: -0.0001

Data Index: 1614396 (Python Code)

Max Activating Token Index: 696

Text #19

Max Range: 0.1052. Min Range: -0.1052

Max Act: 0.0801. Min Act: -0.0001

Data Index: 1257429 (C4 (Web Text))

Max Activating Token Index: 857