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

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

Neuron 518 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.4053. Min Act: -0.0001

Data Index: 1453743 (Python Code)

Max Activating Token Index: 851

Text #1

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3356. Min Act: -0.0001

Data Index: 1605707 (Python Code)

Max Activating Token Index: 61

Text #2

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3373. Min Act: -0.0001

Data Index: 1470004 (Python Code)

Max Activating Token Index: 658

Text #3

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3110. Min Act: -0.0001

Data Index: 1436511 (Python Code)

Max Activating Token Index: 432

Text #4

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2936. Min Act: -0.0001

Data Index: 1439716 (Python Code)

Max Activating Token Index: 312

Text #5

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2905. Min Act: -0.0001

Data Index: 1503530 (Python Code)

Max Activating Token Index: 684

Text #6

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3283. Min Act: -0.0001

Data Index: 1250961 (C4 (Web Text))

Max Activating Token Index: 31

Text #7

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2918. Min Act: -0.0001

Data Index: 940589 (C4 (Web Text))

Max Activating Token Index: 706

Text #8

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2992. Min Act: -0.0001

Data Index: 1058429 (C4 (Web Text))

Max Activating Token Index: 584

Text #9

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.3053. Min Act: -0.0001

Data Index: 1411334 (Python Code)

Max Activating Token Index: 655

Text #10

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2855. Min Act: -0.0001

Data Index: 1016060 (C4 (Web Text))

Max Activating Token Index: 174

Text #11

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2765. Min Act: -0.0001

Data Index: 1508752 (Python Code)

Max Activating Token Index: 892

Text #12

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2902. Min Act: -0.0001

Data Index: 1445684 (Python Code)

Max Activating Token Index: 373

Text #13

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2785. Min Act: -0.0001

Data Index: 1526619 (Python Code)

Max Activating Token Index: 769

Text #14

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2653. Min Act: -0.0001

Data Index: 1196579 (C4 (Web Text))

Max Activating Token Index: 607

Text #15

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2611. Min Act: -0.0001

Data Index: 1563966 (Python Code)

Max Activating Token Index: 280

Text #16

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2531. Min Act: -0.0001

Data Index: 1566433 (Python Code)

Max Activating Token Index: 556

Text #17

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2484. Min Act: -0.0001

Data Index: 1511108 (Python Code)

Max Activating Token Index: 252

Text #18

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2284. Min Act: -0.0001

Data Index: 506856 (C4 (Web Text))

Max Activating Token Index: 253

Text #19

Max Range: 0.4053. Min Range: -0.4053

Max Act: 0.2328. Min Act: -0.0001

Data Index: 1267714 (C4 (Web Text))

Max Activating Token Index: 962