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

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

Neuron 3271 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.3937. Min Act: -0.0001

Data Index: 771264 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1394. Min Act: -0.0001

Data Index: 685740 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.1208. Min Act: -0.0001

Data Index: 245983 (C4 (Web Text))

Max Activating Token Index: 60

Text #3

Max Range: 3.3937. Min Range: -3.3937

Max Act: 3.0235. Min Act: -0.0000

Data Index: 959859 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.9889. Min Act: -0.0001

Data Index: 801868 (C4 (Web Text))

Max Activating Token Index: 34

Text #5

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.8359. Min Act: -0.0001

Data Index: 932795 (C4 (Web Text))

Max Activating Token Index: 217

Text #6

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.8250. Min Act: -0.0001

Data Index: 611038 (C4 (Web Text))

Max Activating Token Index: 410

Text #7

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.8321. Min Act: -0.0001

Data Index: 813595 (C4 (Web Text))

Max Activating Token Index: 237

Text #8

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.6431. Min Act: -0.0001

Data Index: 1174093 (C4 (Web Text))

Max Activating Token Index: 685

Text #9

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.7777. Min Act: -0.0001

Data Index: 1105915 (C4 (Web Text))

Max Activating Token Index: 248

Text #10

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.7707. Min Act: -0.0000

Data Index: 200740 (C4 (Web Text))

Max Activating Token Index: 33

Text #11

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.9023. Min Act: -0.0001

Data Index: 88494 (C4 (Web Text))

Max Activating Token Index: 360

Text #12

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.7691. Min Act: -0.0001

Data Index: 1177867 (C4 (Web Text))

Max Activating Token Index: 772

Text #13

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.8903. Min Act: -0.0000

Data Index: 753737 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.7206. Min Act: -0.0001

Data Index: 311967 (C4 (Web Text))

Max Activating Token Index: 233

Text #15

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.6918. Min Act: -0.0001

Data Index: 538280 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.6903. Min Act: -0.0000

Data Index: 919969 (C4 (Web Text))

Max Activating Token Index: 862

Text #17

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.6934. Min Act: -0.0001

Data Index: 1137623 (C4 (Web Text))

Max Activating Token Index: 519

Text #18

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.6837. Min Act: -0.0000

Data Index: 413309 (C4 (Web Text))

Max Activating Token Index: 46

Text #19

Max Range: 3.3937. Min Range: -3.3937

Max Act: 2.8321. Min Act: -0.0000

Data Index: 642837 (C4 (Web Text))

Max Activating Token Index: 656