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

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

Neuron 1085 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.2133. Min Act: -0.0000

Data Index: 230983 (C4 (Web Text))

Max Activating Token Index: 163

Text #1

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1964. Min Act: -0.0000

Data Index: 1085491 (C4 (Web Text))

Max Activating Token Index: 805

Text #2

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1978. Min Act: -0.0001

Data Index: 1333859 (C4 (Web Text))

Max Activating Token Index: 155

Text #3

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1961. Min Act: -0.0000

Data Index: 983229 (C4 (Web Text))

Max Activating Token Index: 728

Text #4

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1945. Min Act: -0.0001

Data Index: 485284 (C4 (Web Text))

Max Activating Token Index: 59

Text #5

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.2030. Min Act: -0.0000

Data Index: 1327604 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1855. Min Act: -0.0001

Data Index: 1062749 (C4 (Web Text))

Max Activating Token Index: 135

Text #7

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1793. Min Act: -0.0000

Data Index: 1118816 (C4 (Web Text))

Max Activating Token Index: 885

Text #8

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1710. Min Act: -0.0000

Data Index: 932246 (C4 (Web Text))

Max Activating Token Index: 727

Text #9

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1828. Min Act: -0.0000

Data Index: 1243411 (C4 (Web Text))

Max Activating Token Index: 729

Text #10

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1824. Min Act: -0.0001

Data Index: 163994 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1756. Min Act: -0.0000

Data Index: 722296 (C4 (Web Text))

Max Activating Token Index: 128

Text #12

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1758. Min Act: -0.0001

Data Index: 8394 (C4 (Web Text))

Max Activating Token Index: 237

Text #13

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1792. Min Act: -0.0000

Data Index: 1271301 (C4 (Web Text))

Max Activating Token Index: 282

Text #14

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1720. Min Act: -0.0001

Data Index: 1214531 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1319411 (C4 (Web Text))

Max Activating Token Index: 625

Text #16

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1790. Min Act: -0.0000

Data Index: 910985 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1789. Min Act: -0.0001

Data Index: 374111 (C4 (Web Text))

Max Activating Token Index: 215

Text #18

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1711. Min Act: -0.0001

Data Index: 277743 (C4 (Web Text))

Max Activating Token Index: 649

Text #19

Max Range: 0.2133. Min Range: -0.2133

Max Act: 0.1601. Min Act: -0.0001

Data Index: 199169 (C4 (Web Text))

Max Activating Token Index: 755