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

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

Neuron 3314 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: 1.5232. Min Range: -1.5232

Max Act: 1.5232. Min Act: -0.0000

Data Index: 128309 (C4 (Web Text))

Max Activating Token Index: 114

Text #1

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.2540. Min Act: -0.0000

Data Index: 945807 (C4 (Web Text))

Max Activating Token Index: 696

Text #2

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.1095. Min Act: -0.0000

Data Index: 90493 (C4 (Web Text))

Max Activating Token Index: 833

Text #3

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0848. Min Act: -0.0000

Data Index: 805915 (C4 (Web Text))

Max Activating Token Index: 915

Text #4

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0667. Min Act: -0.0000

Data Index: 686428 (C4 (Web Text))

Max Activating Token Index: 850

Text #5

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9913. Min Act: -0.0000

Data Index: 495605 (C4 (Web Text))

Max Activating Token Index: 807

Text #6

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0812. Min Act: -0.0000

Data Index: 928604 (C4 (Web Text))

Max Activating Token Index: 656

Text #7

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9204. Min Act: -0.0000

Data Index: 1139011 (C4 (Web Text))

Max Activating Token Index: 97

Text #8

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0510. Min Act: -0.0000

Data Index: 802309 (C4 (Web Text))

Max Activating Token Index: 915

Text #9

Max Range: 1.5232. Min Range: -1.5232

Max Act: 1.0938. Min Act: -0.0000

Data Index: 915568 (C4 (Web Text))

Max Activating Token Index: 279

Text #10

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.7840. Min Act: -0.0000

Data Index: 118725 (C4 (Web Text))

Max Activating Token Index: 930

Text #11

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9619. Min Act: -0.0000

Data Index: 890316 (C4 (Web Text))

Max Activating Token Index: 490

Text #12

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9217. Min Act: -0.0000

Data Index: 636389 (C4 (Web Text))

Max Activating Token Index: 104

Text #13

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1161230 (C4 (Web Text))

Max Activating Token Index: 191

Text #14

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.8698. Min Act: -0.0000

Data Index: 241390 (C4 (Web Text))

Max Activating Token Index: 668

Text #15

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9406. Min Act: -0.0000

Data Index: 1329576 (C4 (Web Text))

Max Activating Token Index: 378

Text #16

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.8154. Min Act: -0.0000

Data Index: 745908 (C4 (Web Text))

Max Activating Token Index: 150

Text #17

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.8869. Min Act: -0.0000

Data Index: 383867 (C4 (Web Text))

Max Activating Token Index: 68

Text #18

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.8042. Min Act: -0.0000

Data Index: 1043420 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 1.5232. Min Range: -1.5232

Max Act: 0.9094. Min Act: -0.0000

Data Index: 1087623 (C4 (Web Text))

Max Activating Token Index: 818