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

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

Neuron 1607 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.6187. Min Act: -0.0001

Data Index: 155585 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5715. Min Act: -0.0001

Data Index: 33707 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5966. Min Act: -0.0001

Data Index: 1268420 (C4 (Web Text))

Max Activating Token Index: 432

Text #3

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5809. Min Act: -0.0001

Data Index: 211959 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5390. Min Act: -0.0001

Data Index: 910303 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5754. Min Act: -0.0001

Data Index: 1260782 (C4 (Web Text))

Max Activating Token Index: 390

Text #6

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5650. Min Act: -0.0001

Data Index: 1435099 (Python Code)

Max Activating Token Index: 7

Text #7

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5650. Min Act: -0.0001

Data Index: 1402827 (Python Code)

Max Activating Token Index: 7

Text #8

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5617. Min Act: -0.0001

Data Index: 714776 (C4 (Web Text))

Max Activating Token Index: 48

Text #9

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5050. Min Act: -0.0001

Data Index: 411033 (C4 (Web Text))

Max Activating Token Index: 415

Text #10

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5327. Min Act: -0.0001

Data Index: 1170662 (C4 (Web Text))

Max Activating Token Index: 762

Text #11

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5089. Min Act: -0.0001

Data Index: 87330 (C4 (Web Text))

Max Activating Token Index: 683

Text #12

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5484. Min Act: -0.0001

Data Index: 707915 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5468. Min Act: -0.0001

Data Index: 959299 (C4 (Web Text))

Max Activating Token Index: 362

Text #14

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5254. Min Act: -0.0001

Data Index: 75763 (C4 (Web Text))

Max Activating Token Index: 369

Text #15

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5124. Min Act: -0.0001

Data Index: 1202780 (C4 (Web Text))

Max Activating Token Index: 965

Text #16

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5081. Min Act: -0.0001

Data Index: 867031 (C4 (Web Text))

Max Activating Token Index: 276

Text #17

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.5237. Min Act: -0.0001

Data Index: 1112646 (C4 (Web Text))

Max Activating Token Index: 822

Text #18

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4873. Min Act: -0.0001

Data Index: 884905 (C4 (Web Text))

Max Activating Token Index: 502

Text #19

Max Range: 0.6187. Min Range: -0.6187

Max Act: 0.4915. Min Act: -0.0001

Data Index: 1086172 (C4 (Web Text))

Max Activating Token Index: 555