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

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

Neuron 3118 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.9782. Min Act: -0.0000

Data Index: 328867 (C4 (Web Text))

Max Activating Token Index: 215

Text #1

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5733. Min Act: -0.0000

Data Index: 1453591 (Python Code)

Max Activating Token Index: 877

Text #2

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6225. Min Act: -0.0000

Data Index: 1628484 (Python Code)

Max Activating Token Index: 302

Text #3

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5964. Min Act: -0.0000

Data Index: 1535315 (Python Code)

Max Activating Token Index: 772

Text #4

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5765. Min Act: -0.0000

Data Index: 1629186 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.7592. Min Act: -0.0000

Data Index: 1390752 (Python Code)

Max Activating Token Index: 86

Text #6

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6324. Min Act: -0.0000

Data Index: 1424952 (Python Code)

Max Activating Token Index: 676

Text #7

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6288. Min Act: -0.0000

Data Index: 1474136 (Python Code)

Max Activating Token Index: 441

Text #8

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5991. Min Act: -0.0000

Data Index: 1443791 (Python Code)

Max Activating Token Index: 835

Text #9

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6954. Min Act: -0.0000

Data Index: 1481610 (Python Code)

Max Activating Token Index: 833

Text #10

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6927. Min Act: -0.0000

Data Index: 113907 (C4 (Web Text))

Max Activating Token Index: 931

Text #11

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.5743. Min Act: -0.0000

Data Index: 1525028 (Python Code)

Max Activating Token Index: 904

Text #12

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6118. Min Act: -0.0000

Data Index: 1470614 (Python Code)

Max Activating Token Index: 492

Text #13

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.2290. Min Act: -0.0000

Data Index: 1442433 (Python Code)

Max Activating Token Index: 673

Text #14

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.6060. Min Act: -0.0000

Data Index: 1470732 (Python Code)

Max Activating Token Index: 731

Text #15

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.4280. Min Act: -0.0000

Data Index: 1436109 (Python Code)

Max Activating Token Index: 414

Text #16

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.4912. Min Act: -0.0000

Data Index: 1461129 (Python Code)

Max Activating Token Index: 330

Text #17

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.4706. Min Act: -0.0000

Data Index: 1461801 (Python Code)

Max Activating Token Index: 592

Text #18

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.4851. Min Act: -0.0000

Data Index: 1614800 (Python Code)

Max Activating Token Index: 960

Text #19

Max Range: 1.9782. Min Range: -1.9782

Max Act: 1.4539. Min Act: -0.0000

Data Index: 1503850 (Python Code)

Max Activating Token Index: 452