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

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

Neuron 4459 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.7141. Min Act: -0.0000

Data Index: 682612 (C4 (Web Text))

Max Activating Token Index: 23

Text #1

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.4791. Min Act: -0.0000

Data Index: 863539 (C4 (Web Text))

Max Activating Token Index: 313

Text #2

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.4590. Min Act: -0.0000

Data Index: 333949 (C4 (Web Text))

Max Activating Token Index: 351

Text #3

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.4406. Min Act: -0.0000

Data Index: 1102100 (C4 (Web Text))

Max Activating Token Index: 626

Text #4

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.2747. Min Act: 0.0000

Data Index: 1198552 (C4 (Web Text))

Max Activating Token Index: 762

Text #5

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.3843. Min Act: -0.0000

Data Index: 233218 (C4 (Web Text))

Max Activating Token Index: 451

Text #6

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.3599. Min Act: -0.0000

Data Index: 397901 (C4 (Web Text))

Max Activating Token Index: 465

Text #7

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.3312. Min Act: -0.0000

Data Index: 40054 (C4 (Web Text))

Max Activating Token Index: 748

Text #8

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.4106. Min Act: -0.0000

Data Index: 616408 (C4 (Web Text))

Max Activating Token Index: 429

Text #9

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.3360. Min Act: -0.0000

Data Index: 1235328 (C4 (Web Text))

Max Activating Token Index: 329

Text #10

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.3394. Min Act: -0.0000

Data Index: 1025969 (C4 (Web Text))

Max Activating Token Index: 782

Text #11

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.4365. Min Act: -0.0000

Data Index: 210866 (C4 (Web Text))

Max Activating Token Index: 168

Text #12

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.2635. Min Act: -0.0000

Data Index: 608694 (C4 (Web Text))

Max Activating Token Index: 645

Text #13

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.2810. Min Act: -0.0000

Data Index: 540924 (C4 (Web Text))

Max Activating Token Index: 932

Text #14

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.3525. Min Act: -0.0000

Data Index: 914898 (C4 (Web Text))

Max Activating Token Index: 830

Text #15

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.2604. Min Act: -0.0000

Data Index: 451282 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.2945. Min Act: -0.0000

Data Index: 821755 (C4 (Web Text))

Max Activating Token Index: 489

Text #17

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.1999. Min Act: -0.0000

Data Index: 693697 (C4 (Web Text))

Max Activating Token Index: 130

Text #18

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.2624. Min Act: -0.0000

Data Index: 491559 (C4 (Web Text))

Max Activating Token Index: 824

Text #19

Max Range: 1.7141. Min Range: -1.7141

Max Act: 1.2841. Min Act: -0.0000

Data Index: 903342 (C4 (Web Text))

Max Activating Token Index: 368