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

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

Neuron 4966 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Click the toggle to see the full text!

Text #0

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1674. Min Act: -0.0002

Data Index: 1566807 (Python Code)

Max Activating Token Index: 458

Text #1

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1698. Min Act: -0.0001

Data Index: 1372490 (Python Code)

Max Activating Token Index: 484

Text #2

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1686. Min Act: -0.0001

Data Index: 1432843 (Python Code)

Max Activating Token Index: 851

Text #3

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1674. Min Act: -0.0001

Data Index: 1653927 (Python Code)

Max Activating Token Index: 5

Text #4

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1671. Min Act: -0.0001

Data Index: 347578 (C4 (Web Text))

Max Activating Token Index: 3

Text #5

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1672. Min Act: -0.0001

Data Index: 81123 (C4 (Web Text))

Max Activating Token Index: 2

Text #6

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1409964 (Python Code)

Max Activating Token Index: 2

Text #7

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1546888 (Python Code)

Max Activating Token Index: 2

Text #8

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1418250 (Python Code)

Max Activating Token Index: 2

Text #9

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1410137 (Python Code)

Max Activating Token Index: 2

Text #10

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1630205 (Python Code)

Max Activating Token Index: 2

Text #11

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1672. Min Act: -0.0001

Data Index: 1057665 (C4 (Web Text))

Max Activating Token Index: 2

Text #12

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1672. Min Act: -0.0001

Data Index: 371437 (C4 (Web Text))

Max Activating Token Index: 2

Text #13

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1615. Min Act: -0.0002

Data Index: 1486707 (Python Code)

Max Activating Token Index: 562

Text #14

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1615. Min Act: -0.0001

Data Index: 1364710 (Python Code)

Max Activating Token Index: 657

Text #15

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1613. Min Act: -0.0001

Data Index: 1431517 (Python Code)

Max Activating Token Index: 232

Text #16

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1567. Min Act: -0.0001

Data Index: 1162501 (C4 (Web Text))

Max Activating Token Index: 4

Text #17

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1555. Min Act: -0.0001

Data Index: 1592919 (Python Code)

Max Activating Token Index: 59

Text #18

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1549. Min Act: -0.0001

Data Index: 1571227 (Python Code)

Max Activating Token Index: 582

Text #19

Max Range: 0.1698. Min Range: -0.1698

Max Act: 0.1580. Min Act: -0.0001

Data Index: 1069129 (C4 (Web Text))

Max Activating Token Index: 379