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

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

Neuron 967 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.1235. Min Range: -8.1235

Max Act: 8.1235. Min Act: -0.0000

Data Index: 335902 (C4 (Web Text))

Max Activating Token Index: 924

Text #1

Max Range: 8.1235. Min Range: -8.1235

Max Act: 6.4870. Min Act: -0.0000

Data Index: 984373 (C4 (Web Text))

Max Activating Token Index: 58

Text #2

Max Range: 8.1235. Min Range: -8.1235

Max Act: 6.0049. Min Act: -0.0000

Data Index: 897199 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 8.1235. Min Range: -8.1235

Max Act: 6.5701. Min Act: -0.0000

Data Index: 159356 (C4 (Web Text))

Max Activating Token Index: 499

Text #4

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.8181. Min Act: -0.0000

Data Index: 893912 (C4 (Web Text))

Max Activating Token Index: 804

Text #5

Max Range: 8.1235. Min Range: -8.1235

Max Act: 6.0238. Min Act: -0.0000

Data Index: 123384 (C4 (Web Text))

Max Activating Token Index: 366

Text #6

Max Range: 8.1235. Min Range: -8.1235

Max Act: 6.0521. Min Act: -0.0000

Data Index: 625923 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.5857. Min Act: -0.0000

Data Index: 1062869 (C4 (Web Text))

Max Activating Token Index: 71

Text #8

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.6691. Min Act: -0.0000

Data Index: 345774 (C4 (Web Text))

Max Activating Token Index: 546

Text #9

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.4876. Min Act: -0.0000

Data Index: 1211873 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.8014. Min Act: -0.0000

Data Index: 1025220 (C4 (Web Text))

Max Activating Token Index: 927

Text #11

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.5019. Min Act: -0.0000

Data Index: 949384 (C4 (Web Text))

Max Activating Token Index: 1011

Text #12

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.2793. Min Act: -0.0000

Data Index: 1102171 (C4 (Web Text))

Max Activating Token Index: 665

Text #13

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.8389. Min Act: -0.0000

Data Index: 193716 (C4 (Web Text))

Max Activating Token Index: 283

Text #14

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.3944. Min Act: -0.0000

Data Index: 60216 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.3479. Min Act: -0.0000

Data Index: 825792 (C4 (Web Text))

Max Activating Token Index: 104

Text #16

Max Range: 8.1235. Min Range: -8.1235

Max Act: 4.7811. Min Act: -0.0000

Data Index: 490498 (C4 (Web Text))

Max Activating Token Index: 610

Text #17

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.1188. Min Act: -0.0000

Data Index: 87616 (C4 (Web Text))

Max Activating Token Index: 733

Text #18

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.2791. Min Act: -0.0000

Data Index: 119439 (C4 (Web Text))

Max Activating Token Index: 264

Text #19

Max Range: 8.1235. Min Range: -8.1235

Max Act: 5.2816. Min Act: -0.0000

Data Index: 906529 (C4 (Web Text))

Max Activating Token Index: 335