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

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

Neuron 1640 in Layer 0

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: 1.0770. Min Range: -1.0770

Max Act: 1.0745. Min Act: -0.0001

Data Index: 1239568 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0770. Min Act: -0.0001

Data Index: 167781 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0540. Min Act: -0.0001

Data Index: 691227 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0292. Min Act: -0.0001

Data Index: 876282 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0307. Min Act: -0.0001

Data Index: 720101 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0300. Min Act: -0.0001

Data Index: 650396 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0136. Min Act: -0.0002

Data Index: 668992 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0297. Min Act: -0.0001

Data Index: 993632 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0281. Min Act: -0.0001

Data Index: 466364 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0131. Min Act: -0.0001

Data Index: 436155 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9951. Min Act: -0.0001

Data Index: 1280997 (C4 (Web Text))

Max Activating Token Index: 1023

Text #11

Max Range: 1.0770. Min Range: -1.0770

Max Act: 1.0052. Min Act: -0.0001

Data Index: 824754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9874. Min Act: -0.0001

Data Index: 286178 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9745. Min Act: -0.0001

Data Index: 168035 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9857. Min Act: -0.0001

Data Index: 577269 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9841. Min Act: -0.0001

Data Index: 833500 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9799. Min Act: -0.0001

Data Index: 1284223 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9844. Min Act: -0.0001

Data Index: 296561 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9768. Min Act: -0.0001

Data Index: 572288 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 1.0770. Min Range: -1.0770

Max Act: 0.9555. Min Act: -0.0001

Data Index: 201660 (C4 (Web Text))

Max Activating Token Index: 1023