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

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

Neuron 3983 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: 0.9546. Min Range: -0.9546

Max Act: 0.9546. Min Act: -0.0001

Data Index: 1007816 (C4 (Web Text))

Max Activating Token Index: 558

Text #1

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.8312. Min Act: -0.0001

Data Index: 287178 (C4 (Web Text))

Max Activating Token Index: 838

Text #2

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6703. Min Act: -0.0001

Data Index: 1149267 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.7120. Min Act: -0.0001

Data Index: 147472 (C4 (Web Text))

Max Activating Token Index: 127

Text #4

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6877. Min Act: -0.0001

Data Index: 967043 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6484. Min Act: -0.0001

Data Index: 931780 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6661. Min Act: -0.0001

Data Index: 1330737 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6180. Min Act: -0.0001

Data Index: 768626 (C4 (Web Text))

Max Activating Token Index: 398

Text #8

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6259. Min Act: -0.0001

Data Index: 915513 (C4 (Web Text))

Max Activating Token Index: 29

Text #9

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6404. Min Act: -0.0001

Data Index: 924898 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6347. Min Act: -0.0001

Data Index: 443156 (C4 (Web Text))

Max Activating Token Index: 984

Text #11

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.5953. Min Act: -0.0001

Data Index: 1636872 (Python Code)

Max Activating Token Index: 597

Text #12

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6008. Min Act: -0.0001

Data Index: 527386 (C4 (Web Text))

Max Activating Token Index: 506

Text #13

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.5939. Min Act: -0.0001

Data Index: 1132883 (C4 (Web Text))

Max Activating Token Index: 960

Text #14

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.5697. Min Act: -0.0001

Data Index: 765980 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.5713. Min Act: -0.0001

Data Index: 600842 (C4 (Web Text))

Max Activating Token Index: 723

Text #16

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.5879. Min Act: -0.0001

Data Index: 70743 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.5856. Min Act: -0.0001

Data Index: 1197403 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.6300. Min Act: -0.0001

Data Index: 727080 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.9546. Min Range: -0.9546

Max Act: 0.5279. Min Act: -0.0001

Data Index: 727969 (C4 (Web Text))

Max Activating Token Index: 505