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

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

Neuron 4615 in Layer 1

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: 0.4507. Min Range: -0.4507

Max Act: 0.4507. Min Act: -0.0002

Data Index: 972430 (C4 (Web Text))

Max Activating Token Index: 776

Text #1

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4122. Min Act: -0.0002

Data Index: 91697 (C4 (Web Text))

Max Activating Token Index: 200

Text #2

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.4086. Min Act: -0.0002

Data Index: 1325625 (C4 (Web Text))

Max Activating Token Index: 30

Text #3

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3896. Min Act: -0.0003

Data Index: 185738 (C4 (Web Text))

Max Activating Token Index: 347

Text #4

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3923. Min Act: -0.0002

Data Index: 122184 (C4 (Web Text))

Max Activating Token Index: 50

Text #5

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3846. Min Act: -0.0002

Data Index: 880349 (C4 (Web Text))

Max Activating Token Index: 527

Text #6

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3791. Min Act: -0.0002

Data Index: 11752 (C4 (Web Text))

Max Activating Token Index: 148

Text #7

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3862. Min Act: -0.0002

Data Index: 867351 (C4 (Web Text))

Max Activating Token Index: 111

Text #8

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3811. Min Act: -0.0002

Data Index: 682419 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3835. Min Act: -0.0002

Data Index: 1509028 (Python Code)

Max Activating Token Index: 699

Text #10

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3794. Min Act: -0.0002

Data Index: 535703 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3730. Min Act: -0.0002

Data Index: 913580 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3778. Min Act: -0.0002

Data Index: 1137447 (C4 (Web Text))

Max Activating Token Index: 86

Text #13

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3785. Min Act: -0.0002

Data Index: 198111 (C4 (Web Text))

Max Activating Token Index: 8

Text #14

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3665. Min Act: -0.0002

Data Index: 1488482 (Python Code)

Max Activating Token Index: 65

Text #15

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3659. Min Act: -0.0002

Data Index: 768282 (C4 (Web Text))

Max Activating Token Index: 639

Text #16

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3652. Min Act: -0.0002

Data Index: 154587 (C4 (Web Text))

Max Activating Token Index: 570

Text #17

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3645. Min Act: -0.0002

Data Index: 531098 (C4 (Web Text))

Max Activating Token Index: 578

Text #18

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3591. Min Act: -0.0002

Data Index: 868698 (C4 (Web Text))

Max Activating Token Index: 324

Text #19

Max Range: 0.4507. Min Range: -0.4507

Max Act: 0.3581. Min Act: -0.0002

Data Index: 1566083 (Python Code)

Max Activating Token Index: 103