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

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

Neuron 825 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: 1.0189. Min Range: -1.0189

Max Act: 0.9295. Min Act: -0.0001

Data Index: 1287279 (C4 (Web Text))

Max Activating Token Index: 1003

Text #1

Max Range: 1.0189. Min Range: -1.0189

Max Act: 1.0189. Min Act: -0.0001

Data Index: 969277 (C4 (Web Text))

Max Activating Token Index: 499

Text #2

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.9279. Min Act: -0.0001

Data Index: 391794 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.9352. Min Act: -0.0001

Data Index: 526523 (C4 (Web Text))

Max Activating Token Index: 15

Text #4

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.9064. Min Act: -0.0001

Data Index: 524338 (C4 (Web Text))

Max Activating Token Index: 310

Text #5

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.9738. Min Act: -0.0001

Data Index: 1272924 (C4 (Web Text))

Max Activating Token Index: 87

Text #6

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8848. Min Act: -0.0001

Data Index: 946846 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8997. Min Act: -0.0001

Data Index: 41458 (C4 (Web Text))

Max Activating Token Index: 15

Text #8

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8676. Min Act: -0.0001

Data Index: 574305 (C4 (Web Text))

Max Activating Token Index: 67

Text #9

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8508. Min Act: -0.0001

Data Index: 871940 (C4 (Web Text))

Max Activating Token Index: 379

Text #10

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8254. Min Act: -0.0001

Data Index: 1384492 (Python Code)

Max Activating Token Index: 250

Text #11

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8342. Min Act: -0.0001

Data Index: 1060069 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8727. Min Act: -0.0001

Data Index: 882745 (C4 (Web Text))

Max Activating Token Index: 641

Text #13

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8178. Min Act: -0.0001

Data Index: 1022631 (C4 (Web Text))

Max Activating Token Index: 335

Text #14

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8753. Min Act: -0.0001

Data Index: 1315838 (C4 (Web Text))

Max Activating Token Index: 684

Text #15

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8730. Min Act: -0.0001

Data Index: 636511 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8164. Min Act: -0.0001

Data Index: 567490 (C4 (Web Text))

Max Activating Token Index: 601

Text #17

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8488. Min Act: -0.0001

Data Index: 815195 (C4 (Web Text))

Max Activating Token Index: 784

Text #18

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8442. Min Act: -0.0001

Data Index: 290255 (C4 (Web Text))

Max Activating Token Index: 377

Text #19

Max Range: 1.0189. Min Range: -1.0189

Max Act: 0.8075. Min Act: -0.0001

Data Index: 649607 (C4 (Web Text))

Max Activating Token Index: 73