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

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

Neuron 2142 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: 0.1202. Min Range: -0.1202

Max Act: 0.1202. Min Act: -0.0001

Data Index: 486046 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1025. Min Act: -0.0001

Data Index: 826543 (C4 (Web Text))

Max Activating Token Index: 42

Text #2

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0956. Min Act: -0.0001

Data Index: 635704 (C4 (Web Text))

Max Activating Token Index: 275

Text #3

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1064. Min Act: -0.0001

Data Index: 1330209 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0994. Min Act: -0.0001

Data Index: 516926 (C4 (Web Text))

Max Activating Token Index: 1006

Text #5

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1051. Min Act: -0.0001

Data Index: 704841 (C4 (Web Text))

Max Activating Token Index: 120

Text #6

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.1038. Min Act: -0.0001

Data Index: 1073083 (C4 (Web Text))

Max Activating Token Index: 466

Text #7

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0925. Min Act: -0.0001

Data Index: 41149 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0908. Min Act: -0.0001

Data Index: 817937 (C4 (Web Text))

Max Activating Token Index: 728

Text #9

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0961. Min Act: -0.0001

Data Index: 1135888 (C4 (Web Text))

Max Activating Token Index: 898

Text #10

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0916. Min Act: -0.0001

Data Index: 894081 (C4 (Web Text))

Max Activating Token Index: 448

Text #11

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0953. Min Act: -0.0001

Data Index: 678761 (C4 (Web Text))

Max Activating Token Index: 261

Text #12

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0877. Min Act: -0.0001

Data Index: 81229 (C4 (Web Text))

Max Activating Token Index: 215

Text #13

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0833. Min Act: -0.0001

Data Index: 816602 (C4 (Web Text))

Max Activating Token Index: 643

Text #14

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0879. Min Act: -0.0001

Data Index: 613610 (C4 (Web Text))

Max Activating Token Index: 584

Text #15

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0854. Min Act: -0.0001

Data Index: 193627 (C4 (Web Text))

Max Activating Token Index: 53

Text #16

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0820. Min Act: -0.0001

Data Index: 139214 (C4 (Web Text))

Max Activating Token Index: 992

Text #17

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0895. Min Act: -0.0001

Data Index: 376940 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0862. Min Act: -0.0001

Data Index: 867204 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.1202. Min Range: -0.1202

Max Act: 0.0866. Min Act: -0.0001

Data Index: 267693 (C4 (Web Text))

Max Activating Token Index: 793