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

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

Neuron 3593 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1596. Min Range: -1.1596

Max Act: 1.1596. Min Act: -0.0000

Data Index: 895586 (C4 (Web Text))

Max Activating Token Index: 237

Text #1

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9752. Min Act: -0.0000

Data Index: 1219135 (C4 (Web Text))

Max Activating Token Index: 197

Text #2

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8695. Min Act: -0.0000

Data Index: 8634 (C4 (Web Text))

Max Activating Token Index: 342

Text #3

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.9203. Min Act: -0.0000

Data Index: 1065167 (C4 (Web Text))

Max Activating Token Index: 823

Text #4

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8243. Min Act: -0.0000

Data Index: 1276658 (C4 (Web Text))

Max Activating Token Index: 27

Text #5

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8217. Min Act: -0.0000

Data Index: 1356517 (C4 (Web Text))

Max Activating Token Index: 252

Text #6

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.8091. Min Act: -0.0000

Data Index: 1359275 (C4 (Web Text))

Max Activating Token Index: 57

Text #7

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7203. Min Act: -0.0000

Data Index: 1245710 (C4 (Web Text))

Max Activating Token Index: 495

Text #8

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7692. Min Act: -0.0000

Data Index: 898337 (C4 (Web Text))

Max Activating Token Index: 871

Text #9

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.7315. Min Act: -0.0000

Data Index: 56231 (C4 (Web Text))

Max Activating Token Index: 145

Text #10

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6890. Min Act: -0.0000

Data Index: 971199 (C4 (Web Text))

Max Activating Token Index: 745

Text #11

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6915. Min Act: -0.0000

Data Index: 502477 (C4 (Web Text))

Max Activating Token Index: 867

Text #12

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6768. Min Act: -0.0000

Data Index: 1093796 (C4 (Web Text))

Max Activating Token Index: 537

Text #13

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6574. Min Act: -0.0000

Data Index: 470907 (C4 (Web Text))

Max Activating Token Index: 163

Text #14

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6337. Min Act: -0.0000

Data Index: 702351 (C4 (Web Text))

Max Activating Token Index: 567

Text #15

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.5892. Min Act: 0.0000

Data Index: 825962 (C4 (Web Text))

Max Activating Token Index: 998

Text #16

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.5958. Min Act: -0.0000

Data Index: 1357434 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6232. Min Act: -0.0000

Data Index: 357582 (C4 (Web Text))

Max Activating Token Index: 955

Text #18

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6274. Min Act: -0.0000

Data Index: 392214 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.1596. Min Range: -1.1596

Max Act: 0.6248. Min Act: -0.0000

Data Index: 252891 (C4 (Web Text))

Max Activating Token Index: 416