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

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

Neuron 4282 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5080. Min Act: -0.0000

Data Index: 1373442 (Python Code)

Max Activating Token Index: 353

Text #1

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.5547. Min Act: -0.0000

Data Index: 949064 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4459. Min Act: -0.0000

Data Index: 674900 (C4 (Web Text))

Max Activating Token Index: 905

Text #3

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4269. Min Act: -0.0000

Data Index: 1638769 (Python Code)

Max Activating Token Index: 487

Text #4

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4507. Min Act: -0.0000

Data Index: 981525 (C4 (Web Text))

Max Activating Token Index: 82

Text #5

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4696. Min Act: -0.0000

Data Index: 362123 (C4 (Web Text))

Max Activating Token Index: 486

Text #6

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.4108. Min Act: -0.0000

Data Index: 591674 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3832. Min Act: -0.0000

Data Index: 1281582 (C4 (Web Text))

Max Activating Token Index: 373

Text #8

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3996. Min Act: -0.0000

Data Index: 813219 (C4 (Web Text))

Max Activating Token Index: 321

Text #9

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3759. Min Act: -0.0000

Data Index: 1046785 (C4 (Web Text))

Max Activating Token Index: 47

Text #10

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3772. Min Act: -0.0001

Data Index: 1501505 (Python Code)

Max Activating Token Index: 400

Text #11

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3838. Min Act: -0.0000

Data Index: 127938 (C4 (Web Text))

Max Activating Token Index: 178

Text #12

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3804. Min Act: -0.0000

Data Index: 725175 (C4 (Web Text))

Max Activating Token Index: 1018

Text #13

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3801. Min Act: -0.0000

Data Index: 580725 (C4 (Web Text))

Max Activating Token Index: 889

Text #14

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1259050 (C4 (Web Text))

Max Activating Token Index: 724

Text #15

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3740. Min Act: -0.0000

Data Index: 561266 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3748. Min Act: -0.0000

Data Index: 964984 (C4 (Web Text))

Max Activating Token Index: 493

Text #17

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3516. Min Act: -0.0001

Data Index: 58312 (C4 (Web Text))

Max Activating Token Index: 398

Text #18

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3545. Min Act: -0.0000

Data Index: 441510 (C4 (Web Text))

Max Activating Token Index: 120

Text #19

Max Range: 0.5547. Min Range: -0.5547

Max Act: 0.3734. Min Act: -0.0000

Data Index: 73812 (C4 (Web Text))

Max Activating Token Index: 474