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

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

Neuron 3755 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.2614. Min Act: -0.0001

Data Index: 623039 (C4 (Web Text))

Max Activating Token Index: 975

Text #1

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.0649. Min Act: -0.0000

Data Index: 1214952 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.0815. Min Act: -0.0001

Data Index: 80883 (C4 (Web Text))

Max Activating Token Index: 806

Text #3

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.1095. Min Act: -0.0000

Data Index: 1069311 (C4 (Web Text))

Max Activating Token Index: 41

Text #4

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.1116. Min Act: -0.0000

Data Index: 621163 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.0279. Min Act: -0.0001

Data Index: 242920 (C4 (Web Text))

Max Activating Token Index: 66

Text #6

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9833. Min Act: -0.0000

Data Index: 542678 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 1.2614. Min Range: -1.2614

Max Act: 1.0331. Min Act: -0.0000

Data Index: 211739 (C4 (Web Text))

Max Activating Token Index: 432

Text #8

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9767. Min Act: -0.0000

Data Index: 1342262 (C4 (Web Text))

Max Activating Token Index: 144

Text #9

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9506. Min Act: -0.0001

Data Index: 62668 (C4 (Web Text))

Max Activating Token Index: 158

Text #10

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9274. Min Act: -0.0000

Data Index: 181434 (C4 (Web Text))

Max Activating Token Index: 87

Text #11

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1172831 (C4 (Web Text))

Max Activating Token Index: 570

Text #12

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8753. Min Act: -0.0000

Data Index: 728451 (C4 (Web Text))

Max Activating Token Index: 132

Text #13

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1007351 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1022313 (C4 (Web Text))

Max Activating Token Index: 280

Text #15

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9270. Min Act: -0.0000

Data Index: 819042 (C4 (Web Text))

Max Activating Token Index: 636

Text #16

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9513. Min Act: -0.0001

Data Index: 858309 (C4 (Web Text))

Max Activating Token Index: 775

Text #17

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8825. Min Act: -0.0000

Data Index: 644541 (C4 (Web Text))

Max Activating Token Index: 238

Text #18

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.9126. Min Act: -0.0001

Data Index: 35701 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 1.2614. Min Range: -1.2614

Max Act: 0.8244. Min Act: -0.0001

Data Index: 402713 (C4 (Web Text))

Max Activating Token Index: 236