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

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

Neuron 5968 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('solu-12l')

Click the toggle to see the full text!

Text #0

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1948. Min Act: -0.0002

Data Index: 947430 (C4 (Web Text))

Max Activating Token Index: 423

Text #1

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1931. Min Act: -0.0002

Data Index: 21183 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1445. Min Act: -0.0002

Data Index: 797073 (C4 (Web Text))

Max Activating Token Index: 630

Text #3

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1423. Min Act: -0.0002

Data Index: 625299 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1431. Min Act: -0.0002

Data Index: 1344481 (C4 (Web Text))

Max Activating Token Index: 785

Text #5

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1486. Min Act: -0.0002

Data Index: 876516 (C4 (Web Text))

Max Activating Token Index: 19

Text #6

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1189. Min Act: -0.0002

Data Index: 1273862 (C4 (Web Text))

Max Activating Token Index: 827

Text #7

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1384. Min Act: -0.0003

Data Index: 342603 (C4 (Web Text))

Max Activating Token Index: 827

Text #8

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1369. Min Act: -0.0003

Data Index: 430397 (C4 (Web Text))

Max Activating Token Index: 797

Text #9

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1112. Min Act: -0.0002

Data Index: 171524 (C4 (Web Text))

Max Activating Token Index: 524

Text #10

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1185. Min Act: -0.0002

Data Index: 840881 (C4 (Web Text))

Max Activating Token Index: 909

Text #11

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1182. Min Act: -0.0002

Data Index: 388301 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1140. Min Act: -0.0002

Data Index: 250344 (C4 (Web Text))

Max Activating Token Index: 742

Text #13

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1063. Min Act: -0.0002

Data Index: 1125535 (C4 (Web Text))

Max Activating Token Index: 722

Text #14

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0761. Min Act: -0.0002

Data Index: 185656 (C4 (Web Text))

Max Activating Token Index: 600

Text #15

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0883. Min Act: -0.0002

Data Index: 1253859 (C4 (Web Text))

Max Activating Token Index: 621

Text #16

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0913. Min Act: -0.0002

Data Index: 668136 (C4 (Web Text))

Max Activating Token Index: 290

Text #17

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1007. Min Act: -0.0002

Data Index: 919847 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.1024. Min Act: -0.0002

Data Index: 1287018 (C4 (Web Text))

Max Activating Token Index: 819

Text #19

Max Range: 1.1948. Min Range: -1.1948

Max Act: 1.0731. Min Act: -0.0002

Data Index: 578281 (C4 (Web Text))

Max Activating Token Index: 630