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

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

Neuron 3786 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: 1.1574. Min Range: -1.1574

Max Act: 1.1574. Min Act: -0.0000

Data Index: 635564 (C4 (Web Text))

Max Activating Token Index: 454

Text #1

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.1029. Min Act: -0.0001

Data Index: 309170 (C4 (Web Text))

Max Activating Token Index: 209

Text #2

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0009. Min Act: -0.0000

Data Index: 525864 (C4 (Web Text))

Max Activating Token Index: 572

Text #3

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9982. Min Act: -0.0001

Data Index: 1155473 (C4 (Web Text))

Max Activating Token Index: 146

Text #4

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0001. Min Act: -0.0001

Data Index: 518465 (C4 (Web Text))

Max Activating Token Index: 160

Text #5

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0016. Min Act: -0.0001

Data Index: 631942 (C4 (Web Text))

Max Activating Token Index: 517

Text #6

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9109. Min Act: -0.0000

Data Index: 707392 (C4 (Web Text))

Max Activating Token Index: 30

Text #7

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9491. Min Act: -0.0000

Data Index: 936271 (C4 (Web Text))

Max Activating Token Index: 513

Text #8

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9582. Min Act: -0.0000

Data Index: 1141945 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8571. Min Act: -0.0000

Data Index: 20691 (C4 (Web Text))

Max Activating Token Index: 211

Text #10

Max Range: 1.1574. Min Range: -1.1574

Max Act: 1.0319. Min Act: -0.0001

Data Index: 975804 (C4 (Web Text))

Max Activating Token Index: 800

Text #11

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9279. Min Act: -0.0000

Data Index: 165430 (C4 (Web Text))

Max Activating Token Index: 99

Text #12

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8512. Min Act: -0.0001

Data Index: 1295691 (C4 (Web Text))

Max Activating Token Index: 780

Text #13

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9193. Min Act: -0.0001

Data Index: 784524 (C4 (Web Text))

Max Activating Token Index: 612

Text #14

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8530. Min Act: -0.0000

Data Index: 806144 (C4 (Web Text))

Max Activating Token Index: 359

Text #15

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8624. Min Act: -0.0001

Data Index: 459940 (C4 (Web Text))

Max Activating Token Index: 304

Text #16

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9928. Min Act: -0.0001

Data Index: 10839 (C4 (Web Text))

Max Activating Token Index: 996

Text #17

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1356506 (C4 (Web Text))

Max Activating Token Index: 914

Text #18

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.9116. Min Act: -0.0001

Data Index: 406978 (C4 (Web Text))

Max Activating Token Index: 852

Text #19

Max Range: 1.1574. Min Range: -1.1574

Max Act: 0.8695. Min Act: -0.0001

Data Index: 793121 (C4 (Web Text))

Max Activating Token Index: 539