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

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

Neuron 4803 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: 0.0729. Min Range: -0.0729

Max Act: 0.0729. Min Act: -0.0001

Data Index: 1463000 (Python Code)

Max Activating Token Index: 492

Text #1

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0644. Min Act: -0.0001

Data Index: 331735 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0608. Min Act: -0.0001

Data Index: 21746 (C4 (Web Text))

Max Activating Token Index: 697

Text #3

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0603. Min Act: -0.0001

Data Index: 1135691 (C4 (Web Text))

Max Activating Token Index: 129

Text #4

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0589. Min Act: -0.0001

Data Index: 39406 (C4 (Web Text))

Max Activating Token Index: 405

Text #5

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0595. Min Act: -0.0001

Data Index: 1581596 (Python Code)

Max Activating Token Index: 415

Text #6

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0569. Min Act: -0.0001

Data Index: 312920 (C4 (Web Text))

Max Activating Token Index: 37

Text #7

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0565. Min Act: -0.0001

Data Index: 263383 (C4 (Web Text))

Max Activating Token Index: 641

Text #8

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0576. Min Act: -0.0001

Data Index: 1584167 (Python Code)

Max Activating Token Index: 723

Text #9

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0564. Min Act: -0.0001

Data Index: 1382745 (Python Code)

Max Activating Token Index: 222

Text #10

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0568. Min Act: -0.0001

Data Index: 1152027 (C4 (Web Text))

Max Activating Token Index: 178

Text #11

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0580. Min Act: -0.0001

Data Index: 1579248 (Python Code)

Max Activating Token Index: 770

Text #12

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0567. Min Act: -0.0001

Data Index: 1159202 (C4 (Web Text))

Max Activating Token Index: 755

Text #13

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0560. Min Act: -0.0001

Data Index: 1357255 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0562. Min Act: -0.0001

Data Index: 689164 (C4 (Web Text))

Max Activating Token Index: 68

Text #15

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0562. Min Act: -0.0001

Data Index: 628498 (C4 (Web Text))

Max Activating Token Index: 379

Text #16

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0550. Min Act: -0.0001

Data Index: 121775 (C4 (Web Text))

Max Activating Token Index: 806

Text #17

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0560. Min Act: -0.0002

Data Index: 375552 (C4 (Web Text))

Max Activating Token Index: 93

Text #18

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0553. Min Act: -0.0001

Data Index: 55945 (C4 (Web Text))

Max Activating Token Index: 344

Text #19

Max Range: 0.0729. Min Range: -0.0729

Max Act: 0.0539. Min Act: -0.0001

Data Index: 563725 (C4 (Web Text))

Max Activating Token Index: 677