Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 1405 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.3362. Min Act: -0.0001

Data Index: 785495 (C4 (Web Text))

Max Activating Token Index: 1012

Text #1

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.2852. Min Act: -0.0001

Data Index: 1255136 (C4 (Web Text))

Max Activating Token Index: 775

Text #2

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.3832. Min Act: -0.0001

Data Index: 909767 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.1502. Min Act: -0.0001

Data Index: 356536 (C4 (Web Text))

Max Activating Token Index: 170

Text #4

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.1638. Min Act: -0.0001

Data Index: 967097 (C4 (Web Text))

Max Activating Token Index: 554

Text #5

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.1262. Min Act: -0.0001

Data Index: 1358629 (C4 (Web Text))

Max Activating Token Index: 512

Text #6

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.2184. Min Act: -0.0001

Data Index: 1586380 (Python Code)

Max Activating Token Index: 714

Text #7

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.1235. Min Act: -0.0001

Data Index: 460085 (C4 (Web Text))

Max Activating Token Index: 754

Text #8

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0410. Min Act: -0.0001

Data Index: 840788 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0986. Min Act: -0.0001

Data Index: 213032 (C4 (Web Text))

Max Activating Token Index: 681

Text #10

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0976. Min Act: -0.0001

Data Index: 1281574 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0609. Min Act: -0.0001

Data Index: 736225 (C4 (Web Text))

Max Activating Token Index: 603

Text #12

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.1188. Min Act: -0.0001

Data Index: 1263838 (C4 (Web Text))

Max Activating Token Index: 405

Text #13

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0487. Min Act: -0.0001

Data Index: 145284 (C4 (Web Text))

Max Activating Token Index: 102

Text #14

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0111. Min Act: -0.0001

Data Index: 1054791 (C4 (Web Text))

Max Activating Token Index: 689

Text #15

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0391. Min Act: -0.0001

Data Index: 544023 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0188. Min Act: -0.0001

Data Index: 1294662 (C4 (Web Text))

Max Activating Token Index: 121

Text #17

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0527. Min Act: -0.0001

Data Index: 1290785 (C4 (Web Text))

Max Activating Token Index: 34

Text #18

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0502. Min Act: -0.0001

Data Index: 779303 (C4 (Web Text))

Max Activating Token Index: 209

Text #19

Max Range: 1.3832. Min Range: -1.3832

Max Act: 1.0074. Min Act: -0.0001

Data Index: 324394 (C4 (Web Text))

Max Activating Token Index: 98