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

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

Neuron 98 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0726. Min Act: -0.0002

Data Index: 837558 (C4 (Web Text))

Max Activating Token Index: 99

Text #1

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0342. Min Act: -0.0001

Data Index: 191780 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9758. Min Act: -0.0002

Data Index: 370980 (C4 (Web Text))

Max Activating Token Index: 137

Text #3

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9470. Min Act: -0.0001

Data Index: 1053493 (C4 (Web Text))

Max Activating Token Index: 898

Text #4

Max Range: 1.0726. Min Range: -1.0726

Max Act: 1.0060. Min Act: -0.0002

Data Index: 1308580 (C4 (Web Text))

Max Activating Token Index: 16

Text #5

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9555. Min Act: -0.0002

Data Index: 633438 (C4 (Web Text))

Max Activating Token Index: 123

Text #6

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9419. Min Act: -0.0001

Data Index: 398326 (C4 (Web Text))

Max Activating Token Index: 903

Text #7

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9084. Min Act: -0.0001

Data Index: 1556737 (Python Code)

Max Activating Token Index: 723

Text #8

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9500. Min Act: -0.0001

Data Index: 1162531 (C4 (Web Text))

Max Activating Token Index: 882

Text #9

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8729. Min Act: -0.0001

Data Index: 1577729 (Python Code)

Max Activating Token Index: 61

Text #10

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8739. Min Act: -0.0001

Data Index: 279 (C4 (Web Text))

Max Activating Token Index: 649

Text #11

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9318. Min Act: -0.0002

Data Index: 884013 (C4 (Web Text))

Max Activating Token Index: 149

Text #12

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9159. Min Act: -0.0002

Data Index: 94487 (C4 (Web Text))

Max Activating Token Index: 257

Text #13

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8637. Min Act: -0.0001

Data Index: 396990 (C4 (Web Text))

Max Activating Token Index: 22

Text #14

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8817. Min Act: -0.0002

Data Index: 952513 (C4 (Web Text))

Max Activating Token Index: 35

Text #15

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8215. Min Act: -0.0001

Data Index: 715074 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8418. Min Act: -0.0001

Data Index: 363261 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9449. Min Act: -0.0001

Data Index: 982212 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.8077. Min Act: -0.0001

Data Index: 11417 (C4 (Web Text))

Max Activating Token Index: 826

Text #19

Max Range: 1.0726. Min Range: -1.0726

Max Act: 0.9113. Min Act: -0.0001

Data Index: 1140114 (C4 (Web Text))

Max Activating Token Index: 919