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

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

Neuron 1939 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.2138. Min Act: -0.0001

Data Index: 694675 (C4 (Web Text))

Max Activating Token Index: 438

Text #1

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.0813. Min Act: -0.0001

Data Index: 123452 (C4 (Web Text))

Max Activating Token Index: 517

Text #2

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.1196. Min Act: -0.0001

Data Index: 127290 (C4 (Web Text))

Max Activating Token Index: 655

Text #3

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.1111. Min Act: -0.0001

Data Index: 638951 (C4 (Web Text))

Max Activating Token Index: 826

Text #4

Max Range: 1.2138. Min Range: -1.2138

Max Act: 1.0116. Min Act: -0.0001

Data Index: 1332712 (C4 (Web Text))

Max Activating Token Index: 706

Text #5

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9583. Min Act: -0.0001

Data Index: 695182 (C4 (Web Text))

Max Activating Token Index: 755

Text #6

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8856. Min Act: -0.0001

Data Index: 1327785 (C4 (Web Text))

Max Activating Token Index: 580

Text #7

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9820. Min Act: -0.0001

Data Index: 1152908 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9687. Min Act: -0.0001

Data Index: 1069178 (C4 (Web Text))

Max Activating Token Index: 525

Text #9

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8886. Min Act: -0.0001

Data Index: 372498 (C4 (Web Text))

Max Activating Token Index: 714

Text #10

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.9059. Min Act: -0.0001

Data Index: 1350964 (C4 (Web Text))

Max Activating Token Index: 339

Text #11

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8163. Min Act: -0.0001

Data Index: 756269 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8297. Min Act: -0.0001

Data Index: 913432 (C4 (Web Text))

Max Activating Token Index: 97

Text #13

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8416. Min Act: -0.0001

Data Index: 1237439 (C4 (Web Text))

Max Activating Token Index: 105

Text #14

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8069. Min Act: -0.0001

Data Index: 261949 (C4 (Web Text))

Max Activating Token Index: 480

Text #15

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.7947. Min Act: -0.0001

Data Index: 666944 (C4 (Web Text))

Max Activating Token Index: 737

Text #16

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.7769. Min Act: -0.0001

Data Index: 1010262 (C4 (Web Text))

Max Activating Token Index: 478

Text #17

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8079. Min Act: -0.0001

Data Index: 305868 (C4 (Web Text))

Max Activating Token Index: 731

Text #18

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.8249. Min Act: -0.0001

Data Index: 1266906 (C4 (Web Text))

Max Activating Token Index: 791

Text #19

Max Range: 1.2138. Min Range: -1.2138

Max Act: 0.7677. Min Act: -0.0001

Data Index: 873491 (C4 (Web Text))

Max Activating Token Index: 234