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

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

Neuron 2288 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4583. Min Act: 0.0000

Data Index: 1072826 (C4 (Web Text))

Max Activating Token Index: 55

Text #1

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.4551. Min Act: -0.0000

Data Index: 317983 (C4 (Web Text))

Max Activating Token Index: 472

Text #2

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.3707. Min Act: -0.0000

Data Index: 308598 (C4 (Web Text))

Max Activating Token Index: 33

Text #3

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2427. Min Act: -0.0000

Data Index: 85606 (C4 (Web Text))

Max Activating Token Index: 501

Text #4

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.2234. Min Act: -0.0000

Data Index: 995053 (C4 (Web Text))

Max Activating Token Index: 612

Text #5

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1210752 (C4 (Web Text))

Max Activating Token Index: 776

Text #6

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0495. Min Act: -0.0000

Data Index: 451909 (C4 (Web Text))

Max Activating Token Index: 292

Text #7

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1317886 (C4 (Web Text))

Max Activating Token Index: 868

Text #8

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0581. Min Act: -0.0000

Data Index: 315432 (C4 (Web Text))

Max Activating Token Index: 782

Text #9

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0481. Min Act: -0.0000

Data Index: 392843 (C4 (Web Text))

Max Activating Token Index: 802

Text #10

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0096. Min Act: -0.0000

Data Index: 1157411 (C4 (Web Text))

Max Activating Token Index: 388

Text #11

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0030. Min Act: -0.0000

Data Index: 965873 (C4 (Web Text))

Max Activating Token Index: 387

Text #12

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9952. Min Act: -0.0000

Data Index: 156739 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9924. Min Act: -0.0000

Data Index: 491058 (C4 (Web Text))

Max Activating Token Index: 712

Text #14

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9568. Min Act: -0.0000

Data Index: 528004 (C4 (Web Text))

Max Activating Token Index: 649

Text #15

Max Range: 1.4583. Min Range: -1.4583

Max Act: 1.0602. Min Act: -0.0000

Data Index: 430673 (C4 (Web Text))

Max Activating Token Index: 685

Text #16

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9660. Min Act: -0.0000

Data Index: 833579 (C4 (Web Text))

Max Activating Token Index: 427

Text #17

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9718. Min Act: -0.0000

Data Index: 1234358 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1001159 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 1.4583. Min Range: -1.4583

Max Act: 0.9395. Min Act: 0.0000

Data Index: 277266 (C4 (Web Text))

Max Activating Token Index: 816