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

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

Neuron 1390 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.1590. Min Act: -0.0001

Data Index: 1236706 (C4 (Web Text))

Max Activating Token Index: 147

Text #1

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0422. Min Act: -0.0001

Data Index: 808805 (C4 (Web Text))

Max Activating Token Index: 742

Text #2

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9257. Min Act: -0.0001

Data Index: 311375 (C4 (Web Text))

Max Activating Token Index: 346

Text #3

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9289. Min Act: -0.0001

Data Index: 1021440 (C4 (Web Text))

Max Activating Token Index: 167

Text #4

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9627. Min Act: -0.0001

Data Index: 113471 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9318. Min Act: -0.0001

Data Index: 556255 (C4 (Web Text))

Max Activating Token Index: 259

Text #6

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8709. Min Act: -0.0001

Data Index: 907178 (C4 (Web Text))

Max Activating Token Index: 673

Text #7

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8820. Min Act: -0.0001

Data Index: 763102 (C4 (Web Text))

Max Activating Token Index: 156

Text #8

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8694. Min Act: -0.0001

Data Index: 376018 (C4 (Web Text))

Max Activating Token Index: 648

Text #9

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9299. Min Act: -0.0001

Data Index: 787222 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 1.1590. Min Range: -1.1590

Max Act: 1.0834. Min Act: -0.0001

Data Index: 1048783 (C4 (Web Text))

Max Activating Token Index: 419

Text #11

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9664. Min Act: -0.0001

Data Index: 691588 (C4 (Web Text))

Max Activating Token Index: 236

Text #12

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7969. Min Act: -0.0001

Data Index: 784415 (C4 (Web Text))

Max Activating Token Index: 198

Text #13

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9393. Min Act: -0.0001

Data Index: 1105526 (C4 (Web Text))

Max Activating Token Index: 338

Text #14

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.9607. Min Act: -0.0001

Data Index: 479620 (C4 (Web Text))

Max Activating Token Index: 849

Text #15

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8941. Min Act: -0.0001

Data Index: 971211 (C4 (Web Text))

Max Activating Token Index: 286

Text #16

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8889. Min Act: -0.0001

Data Index: 1283579 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7470. Min Act: -0.0001

Data Index: 172844 (C4 (Web Text))

Max Activating Token Index: 827

Text #18

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.7202. Min Act: -0.0001

Data Index: 984140 (C4 (Web Text))

Max Activating Token Index: 401

Text #19

Max Range: 1.1590. Min Range: -1.1590

Max Act: 0.8560. Min Act: -0.0001

Data Index: 769729 (C4 (Web Text))

Max Activating Token Index: 449