Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3684 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 2.4561. Min Range: -2.4561

Max Act: 2.4561. Min Act: -0.0000

Data Index: 778990 (C4 (Web Text))

Max Activating Token Index: 620

Text #1

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.9248. Min Act: -0.0000

Data Index: 1182040 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.9128. Min Act: -0.0000

Data Index: 1337468 (C4 (Web Text))

Max Activating Token Index: 347

Text #3

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.9035. Min Act: -0.0000

Data Index: 204055 (C4 (Web Text))

Max Activating Token Index: 309

Text #4

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.6762. Min Act: -0.0000

Data Index: 1189788 (C4 (Web Text))

Max Activating Token Index: 244

Text #5

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.8325. Min Act: -0.0000

Data Index: 1059755 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7317. Min Act: -0.0000

Data Index: 128070 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7268. Min Act: -0.0000

Data Index: 68179 (C4 (Web Text))

Max Activating Token Index: 898

Text #8

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.8923. Min Act: -0.0000

Data Index: 162104 (C4 (Web Text))

Max Activating Token Index: 73

Text #9

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7491. Min Act: -0.0000

Data Index: 421247 (C4 (Web Text))

Max Activating Token Index: 440

Text #10

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7070. Min Act: -0.0000

Data Index: 614362 (C4 (Web Text))

Max Activating Token Index: 977

Text #11

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.6251. Min Act: -0.0000

Data Index: 364588 (C4 (Web Text))

Max Activating Token Index: 239

Text #12

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.6948. Min Act: -0.0000

Data Index: 842422 (C4 (Web Text))

Max Activating Token Index: 518

Text #13

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.5674. Min Act: -0.0000

Data Index: 1322352 (C4 (Web Text))

Max Activating Token Index: 1021

Text #14

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7415. Min Act: -0.0000

Data Index: 72465 (C4 (Web Text))

Max Activating Token Index: 833

Text #15

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7224. Min Act: -0.0000

Data Index: 68662 (C4 (Web Text))

Max Activating Token Index: 844

Text #16

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.7099. Min Act: -0.0000

Data Index: 1124981 (C4 (Web Text))

Max Activating Token Index: 794

Text #17

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.6088. Min Act: -0.0000

Data Index: 1303517 (C4 (Web Text))

Max Activating Token Index: 562

Text #18

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.6854. Min Act: -0.0000

Data Index: 1049352 (C4 (Web Text))

Max Activating Token Index: 169

Text #19

Max Range: 2.4561. Min Range: -2.4561

Max Act: 1.5973. Min Act: -0.0000

Data Index: 721442 (C4 (Web Text))

Max Activating Token Index: 563