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

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

Neuron 89 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1905. Min Range: -1.1905

Max Act: 1.1905. Min Act: -0.0000

Data Index: 1033547 (C4 (Web Text))

Max Activating Token Index: 1021

Text #1

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.7487. Min Act: -0.0000

Data Index: 199621 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.6402. Min Act: -0.0000

Data Index: 1506266 (Python Code)

Max Activating Token Index: 726

Text #3

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.6040. Min Act: -0.0000

Data Index: 1378549 (Python Code)

Max Activating Token Index: 979

Text #4

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.6267. Min Act: -0.0000

Data Index: 892330 (C4 (Web Text))

Max Activating Token Index: 76

Text #5

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.5307. Min Act: -0.0001

Data Index: 1565659 (Python Code)

Max Activating Token Index: 144

Text #6

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.5221. Min Act: -0.0000

Data Index: 1603354 (Python Code)

Max Activating Token Index: 178

Text #7

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.5030. Min Act: -0.0000

Data Index: 1608173 (Python Code)

Max Activating Token Index: 260

Text #8

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.5291. Min Act: -0.0000

Data Index: 1487528 (Python Code)

Max Activating Token Index: 687

Text #9

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.5246. Min Act: -0.0000

Data Index: 1160102 (C4 (Web Text))

Max Activating Token Index: 423

Text #10

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4831. Min Act: -0.0000

Data Index: 910077 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1374580 (Python Code)

Max Activating Token Index: 1006

Text #12

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4765. Min Act: -0.0000

Data Index: 839691 (C4 (Web Text))

Max Activating Token Index: 192

Text #13

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4811. Min Act: -0.0000

Data Index: 652102 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4728. Min Act: -0.0000

Data Index: 942315 (C4 (Web Text))

Max Activating Token Index: 394

Text #15

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.5053. Min Act: -0.0000

Data Index: 1429036 (Python Code)

Max Activating Token Index: 636

Text #16

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4868. Min Act: -0.0000

Data Index: 1560710 (Python Code)

Max Activating Token Index: 230

Text #17

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4780. Min Act: -0.0000

Data Index: 1117380 (C4 (Web Text))

Max Activating Token Index: 847

Text #18

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4662. Min Act: -0.0000

Data Index: 1178508 (C4 (Web Text))

Max Activating Token Index: 363

Text #19

Max Range: 1.1905. Min Range: -1.1905

Max Act: 0.4594. Min Act: -0.0000

Data Index: 71819 (C4 (Web Text))

Max Activating Token Index: 101