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

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

Neuron 1072 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.7648. Min Act: -0.0000

Data Index: 371174 (C4 (Web Text))

Max Activating Token Index: 373

Text #1

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3955. Min Act: -0.0000

Data Index: 281112 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3269. Min Act: -0.0000

Data Index: 495882 (C4 (Web Text))

Max Activating Token Index: 479

Text #3

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3714. Min Act: -0.0000

Data Index: 851115 (C4 (Web Text))

Max Activating Token Index: 1000

Text #4

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3696. Min Act: -0.0000

Data Index: 157012 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3249. Min Act: -0.0000

Data Index: 1341625 (C4 (Web Text))

Max Activating Token Index: 162

Text #6

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.2553. Min Act: -0.0000

Data Index: 831403 (C4 (Web Text))

Max Activating Token Index: 492

Text #7

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.3353. Min Act: -0.0000

Data Index: 396949 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.2215. Min Act: -0.0000

Data Index: 608843 (C4 (Web Text))

Max Activating Token Index: 576

Text #9

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1001172 (C4 (Web Text))

Max Activating Token Index: 591

Text #10

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.1774. Min Act: -0.0000

Data Index: 1091177 (C4 (Web Text))

Max Activating Token Index: 559

Text #11

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.1579. Min Act: -0.0000

Data Index: 586022 (C4 (Web Text))

Max Activating Token Index: 146

Text #12

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.1270. Min Act: -0.0000

Data Index: 1168914 (C4 (Web Text))

Max Activating Token Index: 181

Text #13

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.0758. Min Act: -0.0000

Data Index: 430032 (C4 (Web Text))

Max Activating Token Index: 425

Text #14

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.0597. Min Act: -0.0000

Data Index: 430091 (C4 (Web Text))

Max Activating Token Index: 404

Text #15

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.0760. Min Act: -0.0000

Data Index: 301462 (C4 (Web Text))

Max Activating Token Index: 1018

Text #16

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.0623. Min Act: -0.0000

Data Index: 1264951 (C4 (Web Text))

Max Activating Token Index: 598

Text #17

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.0554. Min Act: -0.0000

Data Index: 1152312 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.7648. Min Range: -1.7648

Max Act: 0.9646. Min Act: -0.0000

Data Index: 821537 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 1.7648. Min Range: -1.7648

Max Act: 1.0611. Min Act: -0.0000

Data Index: 477181 (C4 (Web Text))

Max Activating Token Index: 673