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

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

Neuron 1859 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.2887. Min Act: -0.0001

Data Index: 305802 (C4 (Web Text))

Max Activating Token Index: 832

Text #1

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.2510. Min Act: -0.0001

Data Index: 158768 (C4 (Web Text))

Max Activating Token Index: 298

Text #2

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.1664. Min Act: -0.0001

Data Index: 839606 (C4 (Web Text))

Max Activating Token Index: 556

Text #3

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0002. Min Act: -0.0001

Data Index: 1348074 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0942. Min Act: -0.0001

Data Index: 314257 (C4 (Web Text))

Max Activating Token Index: 453

Text #5

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0620. Min Act: -0.0001

Data Index: 526291 (C4 (Web Text))

Max Activating Token Index: 291

Text #6

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0117. Min Act: -0.0001

Data Index: 243806 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0949. Min Act: -0.0001

Data Index: 1258936 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.9922. Min Act: -0.0001

Data Index: 555233 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.9872. Min Act: -0.0001

Data Index: 493218 (C4 (Web Text))

Max Activating Token Index: 449

Text #10

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.1063. Min Act: -0.0001

Data Index: 1102302 (C4 (Web Text))

Max Activating Token Index: 138

Text #11

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0768. Min Act: -0.0001

Data Index: 1325681 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.9322. Min Act: -0.0001

Data Index: 701190 (C4 (Web Text))

Max Activating Token Index: 907

Text #13

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0603. Min Act: -0.0001

Data Index: 501898 (C4 (Web Text))

Max Activating Token Index: 126

Text #14

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0903. Min Act: -0.0001

Data Index: 186955 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.9043. Min Act: -0.0001

Data Index: 493403 (C4 (Web Text))

Max Activating Token Index: 638

Text #16

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0195. Min Act: -0.0001

Data Index: 745160 (C4 (Web Text))

Max Activating Token Index: 916

Text #17

Max Range: 1.2887. Min Range: -1.2887

Max Act: 1.0397. Min Act: -0.0001

Data Index: 514010 (C4 (Web Text))

Max Activating Token Index: 726

Text #18

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.8516. Min Act: -0.0001

Data Index: 1018749 (C4 (Web Text))

Max Activating Token Index: 329

Text #19

Max Range: 1.2887. Min Range: -1.2887

Max Act: 0.9638. Min Act: -0.0001

Data Index: 113554 (C4 (Web Text))

Max Activating Token Index: 97