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

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

Neuron 2263 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4853. Min Act: -0.0001

Data Index: 186314 (C4 (Web Text))

Max Activating Token Index: 38

Text #1

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4914. Min Act: -0.0001

Data Index: 548091 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4839. Min Act: -0.0001

Data Index: 1167315 (C4 (Web Text))

Max Activating Token Index: 844

Text #3

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4705. Min Act: -0.0001

Data Index: 672832 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4833. Min Act: -0.0001

Data Index: 674485 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4344. Min Act: -0.0001

Data Index: 595791 (C4 (Web Text))

Max Activating Token Index: 916

Text #6

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4492. Min Act: -0.0001

Data Index: 943888 (C4 (Web Text))

Max Activating Token Index: 814

Text #7

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4131. Min Act: -0.0001

Data Index: 946179 (C4 (Web Text))

Max Activating Token Index: 387

Text #8

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4125. Min Act: -0.0001

Data Index: 803808 (C4 (Web Text))

Max Activating Token Index: 61

Text #9

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4240. Min Act: -0.0001

Data Index: 1109372 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4098. Min Act: -0.0001

Data Index: 907683 (C4 (Web Text))

Max Activating Token Index: 544

Text #11

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4228. Min Act: -0.0001

Data Index: 640214 (C4 (Web Text))

Max Activating Token Index: 34

Text #12

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4175. Min Act: -0.0001

Data Index: 413060 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.3877. Min Act: -0.0001

Data Index: 935501 (C4 (Web Text))

Max Activating Token Index: 975

Text #14

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.3863. Min Act: -0.0001

Data Index: 937324 (C4 (Web Text))

Max Activating Token Index: 841

Text #15

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.3849. Min Act: -0.0001

Data Index: 713383 (C4 (Web Text))

Max Activating Token Index: 542

Text #16

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4213. Min Act: -0.0001

Data Index: 739875 (C4 (Web Text))

Max Activating Token Index: 618

Text #17

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.4098. Min Act: -0.0001

Data Index: 235899 (C4 (Web Text))

Max Activating Token Index: 1001

Text #18

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.3913. Min Act: -0.0001

Data Index: 1332777 (C4 (Web Text))

Max Activating Token Index: 928

Text #19

Max Range: 0.4914. Min Range: -0.4914

Max Act: 0.3921. Min Act: -0.0001

Data Index: 861372 (C4 (Web Text))

Max Activating Token Index: 266