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

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

Neuron 543 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.5826. Min Range: -3.5826

Max Act: 3.5826. Min Act: -0.0000

Data Index: 101373 (C4 (Web Text))

Max Activating Token Index: 919

Text #1

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.5544. Min Act: -0.0000

Data Index: 1457504 (Python Code)

Max Activating Token Index: 160

Text #2

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.3834. Min Act: -0.0000

Data Index: 1380331 (Python Code)

Max Activating Token Index: 116

Text #3

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.3545. Min Act: -0.0000

Data Index: 1364173 (Python Code)

Max Activating Token Index: 119

Text #4

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.6329. Min Act: -0.0000

Data Index: 1392659 (Python Code)

Max Activating Token Index: 108

Text #5

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.4618. Min Act: -0.0000

Data Index: 387315 (C4 (Web Text))

Max Activating Token Index: 167

Text #6

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.3008. Min Act: -0.0000

Data Index: 1404030 (Python Code)

Max Activating Token Index: 175

Text #7

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.1579. Min Act: -0.0000

Data Index: 1630739 (Python Code)

Max Activating Token Index: 721

Text #8

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.2886. Min Act: -0.0000

Data Index: 77831 (C4 (Web Text))

Max Activating Token Index: 84

Text #9

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.2975. Min Act: -0.0000

Data Index: 1610283 (Python Code)

Max Activating Token Index: 75

Text #10

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.1943. Min Act: -0.0000

Data Index: 1617689 (Python Code)

Max Activating Token Index: 274

Text #11

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.0521. Min Act: -0.0000

Data Index: 1552261 (Python Code)

Max Activating Token Index: 537

Text #12

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.1716. Min Act: -0.0000

Data Index: 1604155 (Python Code)

Max Activating Token Index: 449

Text #13

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.1603. Min Act: -0.0000

Data Index: 1420532 (Python Code)

Max Activating Token Index: 302

Text #14

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.1512. Min Act: -0.0000

Data Index: 1630423 (Python Code)

Max Activating Token Index: 784

Text #15

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.1505. Min Act: -0.0000

Data Index: 313655 (C4 (Web Text))

Max Activating Token Index: 555

Text #16

Max Range: 3.5826. Min Range: -3.5826

Max Act: 2.1722. Min Act: -0.0000

Data Index: 1513572 (Python Code)

Max Activating Token Index: 849

Text #17

Max Range: 3.5826. Min Range: -3.5826

Max Act: 1.9387. Min Act: -0.0000

Data Index: 1611762 (Python Code)

Max Activating Token Index: 212

Text #18

Max Range: 3.5826. Min Range: -3.5826

Max Act: 1.9883. Min Act: -0.0000

Data Index: 1652697 (Python Code)

Max Activating Token Index: 841

Text #19

Max Range: 3.5826. Min Range: -3.5826

Max Act: 1.9803. Min Act: -0.0000

Data Index: 1490910 (Python Code)

Max Activating Token Index: 795