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

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

Neuron 1270 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: 2.0532. Min Range: -2.0532

Max Act: 2.0532. Min Act: -0.0000

Data Index: 1090390 (C4 (Web Text))

Max Activating Token Index: 915

Text #1

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.9815. Min Act: -0.0000

Data Index: 800657 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.7313. Min Act: -0.0000

Data Index: 773329 (C4 (Web Text))

Max Activating Token Index: 771

Text #3

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.2999. Min Act: -0.0000

Data Index: 860814 (C4 (Web Text))

Max Activating Token Index: 355

Text #4

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.3102. Min Act: -0.0000

Data Index: 17825 (C4 (Web Text))

Max Activating Token Index: 664

Text #5

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.2041. Min Act: -0.0000

Data Index: 232639 (C4 (Web Text))

Max Activating Token Index: 596

Text #6

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.1958. Min Act: -0.0000

Data Index: 775406 (C4 (Web Text))

Max Activating Token Index: 625

Text #7

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.1578. Min Act: -0.0000

Data Index: 911255 (C4 (Web Text))

Max Activating Token Index: 74

Text #8

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.1403. Min Act: -0.0000

Data Index: 621053 (C4 (Web Text))

Max Activating Token Index: 31

Text #9

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.1038. Min Act: -0.0000

Data Index: 1005520 (C4 (Web Text))

Max Activating Token Index: 992

Text #10

Max Range: 2.0532. Min Range: -2.0532

Max Act: 0.9618. Min Act: -0.0000

Data Index: 1130774 (C4 (Web Text))

Max Activating Token Index: 611

Text #11

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.0722. Min Act: -0.0000

Data Index: 371870 (C4 (Web Text))

Max Activating Token Index: 327

Text #12

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.0253. Min Act: -0.0000

Data Index: 209328 (C4 (Web Text))

Max Activating Token Index: 840

Text #13

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.0611. Min Act: -0.0000

Data Index: 230392 (C4 (Web Text))

Max Activating Token Index: 268

Text #14

Max Range: 2.0532. Min Range: -2.0532

Max Act: 0.9890. Min Act: -0.0000

Data Index: 1178411 (C4 (Web Text))

Max Activating Token Index: 475

Text #15

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.0143. Min Act: -0.0000

Data Index: 927284 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 2.0532. Min Range: -2.0532

Max Act: 1.0992. Min Act: -0.0000

Data Index: 332532 (C4 (Web Text))

Max Activating Token Index: 590

Text #17

Max Range: 2.0532. Min Range: -2.0532

Max Act: 0.9939. Min Act: -0.0000

Data Index: 397790 (C4 (Web Text))

Max Activating Token Index: 870

Text #18

Max Range: 2.0532. Min Range: -2.0532

Max Act: 0.9336. Min Act: -0.0000

Data Index: 948321 (C4 (Web Text))

Max Activating Token Index: 440

Text #19

Max Range: 2.0532. Min Range: -2.0532

Max Act: 0.9516. Min Act: -0.0000

Data Index: 67933 (C4 (Web Text))

Max Activating Token Index: 537