Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 755 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.5998. Min Act: -0.0000

Data Index: 851264 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.5514. Min Act: -0.0000

Data Index: 9084 (C4 (Web Text))

Max Activating Token Index: 185

Text #2

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.2798. Min Act: -0.0000

Data Index: 661473 (C4 (Web Text))

Max Activating Token Index: 11

Text #3

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.1625. Min Act: -0.0000

Data Index: 1225793 (C4 (Web Text))

Max Activating Token Index: 533

Text #4

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.2088. Min Act: -0.0000

Data Index: 1056553 (C4 (Web Text))

Max Activating Token Index: 600

Text #5

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.1181. Min Act: -0.0000

Data Index: 1284102 (C4 (Web Text))

Max Activating Token Index: 605

Text #6

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0906. Min Act: -0.0000

Data Index: 426183 (C4 (Web Text))

Max Activating Token Index: 203

Text #7

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.1985. Min Act: -0.0000

Data Index: 129591 (C4 (Web Text))

Max Activating Token Index: 191

Text #8

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0038. Min Act: -0.0000

Data Index: 1335404 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.1408. Min Act: -0.0000

Data Index: 773725 (C4 (Web Text))

Max Activating Token Index: 104

Text #10

Max Range: 1.5998. Min Range: -1.5998

Max Act: 0.9852. Min Act: -0.0000

Data Index: 310977 (C4 (Web Text))

Max Activating Token Index: 997

Text #11

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0099. Min Act: -0.0000

Data Index: 878847 (C4 (Web Text))

Max Activating Token Index: 698

Text #12

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0020. Min Act: -0.0000

Data Index: 118652 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0059. Min Act: -0.0000

Data Index: 779375 (C4 (Web Text))

Max Activating Token Index: 886

Text #14

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0305. Min Act: -0.0000

Data Index: 1303755 (C4 (Web Text))

Max Activating Token Index: 502

Text #15

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0029. Min Act: -0.0000

Data Index: 359545 (C4 (Web Text))

Max Activating Token Index: 985

Text #16

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0015. Min Act: -0.0000

Data Index: 1257106 (C4 (Web Text))

Max Activating Token Index: 48

Text #17

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0033. Min Act: -0.0000

Data Index: 270037 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 1.5998. Min Range: -1.5998

Max Act: 1.0319. Min Act: -0.0000

Data Index: 1082832 (C4 (Web Text))

Max Activating Token Index: 343

Text #19

Max Range: 1.5998. Min Range: -1.5998

Max Act: 0.9777. Min Act: -0.0000

Data Index: 351179 (C4 (Web Text))

Max Activating Token Index: 197