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

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

Neuron 5661 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: 0.0640. Min Range: -0.0640

Max Act: 0.0640. Min Act: -0.0001

Data Index: 1239470 (C4 (Web Text))

Max Activating Token Index: 172

Text #1

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0627. Min Act: -0.0001

Data Index: 233595 (C4 (Web Text))

Max Activating Token Index: 8

Text #2

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0627. Min Act: -0.0001

Data Index: 949468 (C4 (Web Text))

Max Activating Token Index: 557

Text #3

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0622. Min Act: -0.0001

Data Index: 511663 (C4 (Web Text))

Max Activating Token Index: 6

Text #4

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0590. Min Act: -0.0001

Data Index: 798147 (C4 (Web Text))

Max Activating Token Index: 381

Text #5

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0589. Min Act: -0.0001

Data Index: 67935 (C4 (Web Text))

Max Activating Token Index: 369

Text #6

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0604. Min Act: -0.0001

Data Index: 439380 (C4 (Web Text))

Max Activating Token Index: 318

Text #7

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0595. Min Act: -0.0001

Data Index: 24753 (C4 (Web Text))

Max Activating Token Index: 369

Text #8

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0571. Min Act: -0.0001

Data Index: 598886 (C4 (Web Text))

Max Activating Token Index: 88

Text #9

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0581. Min Act: -0.0001

Data Index: 1207382 (C4 (Web Text))

Max Activating Token Index: 816

Text #10

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0561. Min Act: -0.0002

Data Index: 915773 (C4 (Web Text))

Max Activating Token Index: 589

Text #11

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0559. Min Act: -0.0001

Data Index: 349097 (C4 (Web Text))

Max Activating Token Index: 326

Text #12

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0566. Min Act: -0.0002

Data Index: 1579167 (Python Code)

Max Activating Token Index: 217

Text #13

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0550. Min Act: -0.0001

Data Index: 970654 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0560. Min Act: -0.0001

Data Index: 947950 (C4 (Web Text))

Max Activating Token Index: 39

Text #15

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0544. Min Act: -0.0001

Data Index: 222215 (C4 (Web Text))

Max Activating Token Index: 399

Text #16

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0548. Min Act: -0.0001

Data Index: 409795 (C4 (Web Text))

Max Activating Token Index: 83

Text #17

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0534. Min Act: -0.0001

Data Index: 250468 (C4 (Web Text))

Max Activating Token Index: 602

Text #18

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0549. Min Act: -0.0001

Data Index: 1538830 (Python Code)

Max Activating Token Index: 61

Text #19

Max Range: 0.0640. Min Range: -0.0640

Max Act: 0.0539. Min Act: -0.0001

Data Index: 108347 (C4 (Web Text))

Max Activating Token Index: 391