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

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

Neuron 556 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: 0.4010. Min Range: -0.4010

Max Act: 0.4010. Min Act: -0.0000

Data Index: 386315 (C4 (Web Text))

Max Activating Token Index: 484

Text #1

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3780. Min Act: -0.0000

Data Index: 232667 (C4 (Web Text))

Max Activating Token Index: 65

Text #2

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.3654. Min Act: -0.0001

Data Index: 35174 (C4 (Web Text))

Max Activating Token Index: 44

Text #3

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2998. Min Act: -0.0001

Data Index: 1325778 (C4 (Web Text))

Max Activating Token Index: 360

Text #4

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2832. Min Act: -0.0000

Data Index: 701862 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2061. Min Act: -0.0000

Data Index: 1094035 (C4 (Web Text))

Max Activating Token Index: 179

Text #6

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2102. Min Act: -0.0000

Data Index: 648159 (C4 (Web Text))

Max Activating Token Index: 504

Text #7

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2363. Min Act: -0.0000

Data Index: 884812 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2794. Min Act: -0.0001

Data Index: 1049037 (C4 (Web Text))

Max Activating Token Index: 222

Text #9

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2429. Min Act: -0.0001

Data Index: 643844 (C4 (Web Text))

Max Activating Token Index: 92

Text #10

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2287. Min Act: -0.0001

Data Index: 952983 (C4 (Web Text))

Max Activating Token Index: 401

Text #11

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2048. Min Act: -0.0001

Data Index: 469804 (C4 (Web Text))

Max Activating Token Index: 14

Text #12

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2588. Min Act: -0.0001

Data Index: 831632 (C4 (Web Text))

Max Activating Token Index: 224

Text #13

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2098. Min Act: -0.0000

Data Index: 1184619 (C4 (Web Text))

Max Activating Token Index: 204

Text #14

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2158. Min Act: -0.0000

Data Index: 533313 (C4 (Web Text))

Max Activating Token Index: 297

Text #15

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.1919. Min Act: -0.0000

Data Index: 25677 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1220258 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2001. Min Act: -0.0001

Data Index: 1175676 (C4 (Web Text))

Max Activating Token Index: 671

Text #18

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.1814. Min Act: -0.0000

Data Index: 788293 (C4 (Web Text))

Max Activating Token Index: 71

Text #19

Max Range: 0.4010. Min Range: -0.4010

Max Act: 0.2032. Min Act: -0.0001

Data Index: 1075731 (C4 (Web Text))

Max Activating Token Index: 260