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

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

Neuron 4639 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.5617. Min Act: -0.0000

Data Index: 1468551 (Python Code)

Max Activating Token Index: 303

Text #1

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.5342. Min Act: -0.0000

Data Index: 163373 (C4 (Web Text))

Max Activating Token Index: 456

Text #2

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4725. Min Act: -0.0000

Data Index: 1295338 (C4 (Web Text))

Max Activating Token Index: 15

Text #3

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4739. Min Act: -0.0000

Data Index: 223403 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4606. Min Act: -0.0000

Data Index: 1038874 (C4 (Web Text))

Max Activating Token Index: 1009

Text #5

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4756. Min Act: -0.0000

Data Index: 125703 (C4 (Web Text))

Max Activating Token Index: 258

Text #6

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4378. Min Act: -0.0000

Data Index: 1628946 (Python Code)

Max Activating Token Index: 772

Text #7

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3960. Min Act: -0.0000

Data Index: 1553317 (Python Code)

Max Activating Token Index: 416

Text #8

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4650. Min Act: -0.0000

Data Index: 1330169 (C4 (Web Text))

Max Activating Token Index: 691

Text #9

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4364. Min Act: 0.0000

Data Index: 254935 (C4 (Web Text))

Max Activating Token Index: 625

Text #10

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1469917 (Python Code)

Max Activating Token Index: 314

Text #11

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4475. Min Act: -0.0000

Data Index: 1403256 (Python Code)

Max Activating Token Index: 455

Text #12

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4449. Min Act: -0.0000

Data Index: 1397518 (Python Code)

Max Activating Token Index: 522

Text #13

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4261. Min Act: -0.0000

Data Index: 403370 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4264. Min Act: -0.0000

Data Index: 613097 (C4 (Web Text))

Max Activating Token Index: 84

Text #15

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1360204 (Python Code)

Max Activating Token Index: 681

Text #16

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.4048. Min Act: -0.0000

Data Index: 512398 (C4 (Web Text))

Max Activating Token Index: 770

Text #17

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3797. Min Act: -0.0000

Data Index: 828734 (C4 (Web Text))

Max Activating Token Index: 225

Text #18

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3917. Min Act: 0.0000

Data Index: 10327 (C4 (Web Text))

Max Activating Token Index: 895

Text #19

Max Range: 0.5617. Min Range: -0.5617

Max Act: 0.3807. Min Act: 0.0000

Data Index: 698199 (C4 (Web Text))

Max Activating Token Index: 34