Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3393 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4700. Min Act: -0.0000

Data Index: 476803 (C4 (Web Text))

Max Activating Token Index: 75

Text #1

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4701. Min Act: -0.0000

Data Index: 762558 (C4 (Web Text))

Max Activating Token Index: 916

Text #2

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4632. Min Act: -0.0000

Data Index: 1087276 (C4 (Web Text))

Max Activating Token Index: 995

Text #3

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4450. Min Act: -0.0000

Data Index: 465115 (C4 (Web Text))

Max Activating Token Index: 860

Text #4

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4105. Min Act: -0.0000

Data Index: 312397 (C4 (Web Text))

Max Activating Token Index: 815

Text #5

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4282. Min Act: -0.0000

Data Index: 351355 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3811. Min Act: -0.0000

Data Index: 1128956 (C4 (Web Text))

Max Activating Token Index: 755

Text #7

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4081. Min Act: -0.0000

Data Index: 960624 (C4 (Web Text))

Max Activating Token Index: 820

Text #8

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.4077. Min Act: -0.0000

Data Index: 708466 (C4 (Web Text))

Max Activating Token Index: 720

Text #9

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3974. Min Act: -0.0000

Data Index: 19293 (C4 (Web Text))

Max Activating Token Index: 437

Text #10

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3858. Min Act: -0.0000

Data Index: 52179 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3818. Min Act: -0.0000

Data Index: 162746 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3888. Min Act: -0.0000

Data Index: 318445 (C4 (Web Text))

Max Activating Token Index: 443

Text #13

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3867. Min Act: -0.0000

Data Index: 801707 (C4 (Web Text))

Max Activating Token Index: 364

Text #14

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3814. Min Act: -0.0000

Data Index: 656500 (C4 (Web Text))

Max Activating Token Index: 755

Text #15

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3655. Min Act: -0.0000

Data Index: 899160 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3674. Min Act: -0.0000

Data Index: 7997 (C4 (Web Text))

Max Activating Token Index: 701

Text #17

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3575. Min Act: -0.0000

Data Index: 644745 (C4 (Web Text))

Max Activating Token Index: 902

Text #18

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3560. Min Act: -0.0000

Data Index: 711071 (C4 (Web Text))

Max Activating Token Index: 431

Text #19

Max Range: 0.4701. Min Range: -0.4701

Max Act: 0.3652. Min Act: -0.0000

Data Index: 660123 (C4 (Web Text))

Max Activating Token Index: 330