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

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

Neuron 5328 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: 1.6110. Min Range: -1.6110

Max Act: 1.6110. Min Act: -0.0000

Data Index: 1302743 (C4 (Web Text))

Max Activating Token Index: 670

Text #1

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.6073. Min Act: -0.0000

Data Index: 419247 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.2498. Min Act: -0.0000

Data Index: 644076 (C4 (Web Text))

Max Activating Token Index: 134

Text #3

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.2852. Min Act: -0.0000

Data Index: 98119 (C4 (Web Text))

Max Activating Token Index: 243

Text #4

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1810. Min Act: -0.0000

Data Index: 514880 (C4 (Web Text))

Max Activating Token Index: 47

Text #5

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.0904. Min Act: -0.0000

Data Index: 468238 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1570. Min Act: -0.0000

Data Index: 1114114 (C4 (Web Text))

Max Activating Token Index: 118

Text #7

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1563. Min Act: -0.0000

Data Index: 671632 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1663. Min Act: -0.0000

Data Index: 1196138 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1276. Min Act: -0.0000

Data Index: 627221 (C4 (Web Text))

Max Activating Token Index: 884

Text #10

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1370. Min Act: -0.0000

Data Index: 1507553 (Python Code)

Max Activating Token Index: 69

Text #11

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.0998. Min Act: -0.0000

Data Index: 1190491 (C4 (Web Text))

Max Activating Token Index: 318

Text #12

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.0831. Min Act: -0.0000

Data Index: 278831 (C4 (Web Text))

Max Activating Token Index: 818

Text #13

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1209. Min Act: -0.0000

Data Index: 60949 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1068. Min Act: -0.0000

Data Index: 1008682 (C4 (Web Text))

Max Activating Token Index: 1021

Text #15

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.0715. Min Act: -0.0000

Data Index: 511409 (C4 (Web Text))

Max Activating Token Index: 714

Text #16

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.0972. Min Act: -0.0000

Data Index: 514057 (C4 (Web Text))

Max Activating Token Index: 627

Text #17

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1073. Min Act: -0.0000

Data Index: 1454010 (Python Code)

Max Activating Token Index: 184

Text #18

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.1067. Min Act: -0.0000

Data Index: 1447095 (Python Code)

Max Activating Token Index: 468

Text #19

Max Range: 1.6110. Min Range: -1.6110

Max Act: 0.0828. Min Act: -0.0000

Data Index: 380971 (C4 (Web Text))

Max Activating Token Index: 855