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

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

Neuron 5625 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.5655. Min Act: -0.0001

Data Index: 51250 (C4 (Web Text))

Max Activating Token Index: 988

Text #1

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.2818. Min Act: -0.0001

Data Index: 811557 (C4 (Web Text))

Max Activating Token Index: 87

Text #2

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.2602. Min Act: -0.0001

Data Index: 691183 (C4 (Web Text))

Max Activating Token Index: 408

Text #3

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.2015. Min Act: -0.0001

Data Index: 1094320 (C4 (Web Text))

Max Activating Token Index: 438

Text #4

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1303. Min Act: -0.0001

Data Index: 79664 (C4 (Web Text))

Max Activating Token Index: 758

Text #5

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.2597. Min Act: -0.0001

Data Index: 69172 (C4 (Web Text))

Max Activating Token Index: 346

Text #6

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1379. Min Act: -0.0001

Data Index: 305069 (C4 (Web Text))

Max Activating Token Index: 1006

Text #7

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1578. Min Act: -0.0001

Data Index: 141467 (C4 (Web Text))

Max Activating Token Index: 22

Text #8

Max Range: 1.5655. Min Range: -1.5655

Max Act: 0.9551. Min Act: -0.0001

Data Index: 687701 (C4 (Web Text))

Max Activating Token Index: 470

Text #9

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1703. Min Act: -0.0001

Data Index: 1321680 (C4 (Web Text))

Max Activating Token Index: 154

Text #10

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1619. Min Act: -0.0001

Data Index: 884470 (C4 (Web Text))

Max Activating Token Index: 582

Text #11

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1372. Min Act: -0.0001

Data Index: 110172 (C4 (Web Text))

Max Activating Token Index: 956

Text #12

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1290. Min Act: -0.0001

Data Index: 450536 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1563. Min Act: -0.0001

Data Index: 1313301 (C4 (Web Text))

Max Activating Token Index: 570

Text #14

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.1075. Min Act: -0.0001

Data Index: 1213672 (C4 (Web Text))

Max Activating Token Index: 934

Text #15

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.0290. Min Act: -0.0001

Data Index: 1064240 (C4 (Web Text))

Max Activating Token Index: 972

Text #16

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.0278. Min Act: -0.0001

Data Index: 936070 (C4 (Web Text))

Max Activating Token Index: 321

Text #17

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.0499. Min Act: -0.0001

Data Index: 793975 (C4 (Web Text))

Max Activating Token Index: 806

Text #18

Max Range: 1.5655. Min Range: -1.5655

Max Act: 0.9866. Min Act: -0.0001

Data Index: 367440 (C4 (Web Text))

Max Activating Token Index: 90

Text #19

Max Range: 1.5655. Min Range: -1.5655

Max Act: 1.0540. Min Act: -0.0001

Data Index: 343620 (C4 (Web Text))

Max Activating Token Index: 5