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

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

Neuron 2233 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0651. Min Act: -0.0000

Data Index: 318106 (C4 (Web Text))

Max Activating Token Index: 1023

Text #1

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0768. Min Act: -0.0000

Data Index: 582132 (C4 (Web Text))

Max Activating Token Index: 1023

Text #2

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0563. Min Act: -0.0000

Data Index: 438556 (C4 (Web Text))

Max Activating Token Index: 1023

Text #3

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0525. Min Act: -0.0000

Data Index: 711714 (C4 (Web Text))

Max Activating Token Index: 1023

Text #4

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0522. Min Act: -0.0000

Data Index: 888041 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0515. Min Act: -0.0000

Data Index: 217217 (C4 (Web Text))

Max Activating Token Index: 1023

Text #6

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0480. Min Act: -0.0000

Data Index: 402648 (C4 (Web Text))

Max Activating Token Index: 1023

Text #7

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0453. Min Act: -0.0000

Data Index: 910395 (C4 (Web Text))

Max Activating Token Index: 1023

Text #8

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0270. Min Act: -0.0000

Data Index: 936847 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0259. Min Act: -0.0000

Data Index: 1262345 (C4 (Web Text))

Max Activating Token Index: 1023

Text #10

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0421. Min Act: -0.0000

Data Index: 1475891 (Python Code)

Max Activating Token Index: 207

Text #11

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0468. Min Act: -0.0000

Data Index: 132387 (C4 (Web Text))

Max Activating Token Index: 1023

Text #12

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0504. Min Act: -0.0000

Data Index: 441730 (C4 (Web Text))

Max Activating Token Index: 1023

Text #13

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0329. Min Act: -0.0000

Data Index: 1110597 (C4 (Web Text))

Max Activating Token Index: 1023

Text #14

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0376. Min Act: -0.0000

Data Index: 691754 (C4 (Web Text))

Max Activating Token Index: 1023

Text #15

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0356. Min Act: -0.0000

Data Index: 999040 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0454. Min Act: -0.0000

Data Index: 394258 (C4 (Web Text))

Max Activating Token Index: 1023

Text #17

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0260. Min Act: -0.0000

Data Index: 1165519 (C4 (Web Text))

Max Activating Token Index: 1023

Text #18

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0234. Min Act: -0.0000

Data Index: 1226543 (C4 (Web Text))

Max Activating Token Index: 1023

Text #19

Max Range: 0.0768. Min Range: -0.0768

Max Act: 0.0114. Min Act: -0.0000

Data Index: 310105 (C4 (Web Text))

Max Activating Token Index: 1023