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

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

Neuron 2525 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.6175. Min Act: -0.0000

Data Index: 920993 (C4 (Web Text))

Max Activating Token Index: 790

Text #1

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4972. Min Act: -0.0000

Data Index: 1205039 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4753. Min Act: -0.0000

Data Index: 881351 (C4 (Web Text))

Max Activating Token Index: 181

Text #3

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.4312. Min Act: -0.0000

Data Index: 1250432 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.3332. Min Act: -0.0000

Data Index: 1276468 (C4 (Web Text))

Max Activating Token Index: 629

Text #5

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.2192. Min Act: -0.0000

Data Index: 849940 (C4 (Web Text))

Max Activating Token Index: 903

Text #6

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.1010. Min Act: -0.0000

Data Index: 573771 (C4 (Web Text))

Max Activating Token Index: 41

Text #7

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.2242. Min Act: -0.0000

Data Index: 1019686 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.1488. Min Act: -0.0000

Data Index: 450931 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0277. Min Act: -0.0000

Data Index: 1354470 (C4 (Web Text))

Max Activating Token Index: 614

Text #10

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0342. Min Act: -0.0000

Data Index: 759700 (C4 (Web Text))

Max Activating Token Index: 373

Text #11

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0571. Min Act: -0.0000

Data Index: 742274 (C4 (Web Text))

Max Activating Token Index: 541

Text #12

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0311. Min Act: -0.0000

Data Index: 59248 (C4 (Web Text))

Max Activating Token Index: 152

Text #13

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0476. Min Act: -0.0000

Data Index: 52107 (C4 (Web Text))

Max Activating Token Index: 152

Text #14

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0298. Min Act: -0.0000

Data Index: 635700 (C4 (Web Text))

Max Activating Token Index: 795

Text #15

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0527. Min Act: -0.0000

Data Index: 9412 (C4 (Web Text))

Max Activating Token Index: 259

Text #16

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0231. Min Act: -0.0000

Data Index: 457755 (C4 (Web Text))

Max Activating Token Index: 270

Text #17

Max Range: 1.6175. Min Range: -1.6175

Max Act: 0.9544. Min Act: -0.0000

Data Index: 226110 (C4 (Web Text))

Max Activating Token Index: 929

Text #18

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0120. Min Act: -0.0000

Data Index: 932149 (C4 (Web Text))

Max Activating Token Index: 812

Text #19

Max Range: 1.6175. Min Range: -1.6175

Max Act: 1.0047. Min Act: -0.0000

Data Index: 631914 (C4 (Web Text))

Max Activating Token Index: 1002