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

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

Neuron 2663 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: 1.1239. Min Range: -1.1239

Max Act: 1.1239. Min Act: -0.0000

Data Index: 190064 (C4 (Web Text))

Max Activating Token Index: 629

Text #1

Max Range: 1.1239. Min Range: -1.1239

Max Act: 1.1085. Min Act: -0.0000

Data Index: 162989 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 1.1239. Min Range: -1.1239

Max Act: 1.1035. Min Act: -0.0000

Data Index: 1151571 (C4 (Web Text))

Max Activating Token Index: 103

Text #3

Max Range: 1.1239. Min Range: -1.1239

Max Act: 1.0315. Min Act: -0.0000

Data Index: 1020859 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 1.1239. Min Range: -1.1239

Max Act: 1.0641. Min Act: -0.0000

Data Index: 1286923 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.1239. Min Range: -1.1239

Max Act: 1.0304. Min Act: -0.0000

Data Index: 465187 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9719. Min Act: -0.0000

Data Index: 69206 (C4 (Web Text))

Max Activating Token Index: 525

Text #7

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9536. Min Act: -0.0000

Data Index: 491914 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9522. Min Act: -0.0000

Data Index: 1022052 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9286. Min Act: -0.0000

Data Index: 335653 (C4 (Web Text))

Max Activating Token Index: 844

Text #10

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9214. Min Act: -0.0000

Data Index: 1052836 (C4 (Web Text))

Max Activating Token Index: 669

Text #11

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9255. Min Act: -0.0000

Data Index: 845854 (C4 (Web Text))

Max Activating Token Index: 474

Text #12

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9263. Min Act: -0.0000

Data Index: 241164 (C4 (Web Text))

Max Activating Token Index: 596

Text #13

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9061. Min Act: -0.0000

Data Index: 126910 (C4 (Web Text))

Max Activating Token Index: 75

Text #14

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.9106. Min Act: -0.0000

Data Index: 976643 (C4 (Web Text))

Max Activating Token Index: 1017

Text #15

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.8507. Min Act: -0.0000

Data Index: 548385 (C4 (Web Text))

Max Activating Token Index: 702

Text #16

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.8944. Min Act: -0.0000

Data Index: 966931 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.8964. Min Act: -0.0000

Data Index: 1167047 (C4 (Web Text))

Max Activating Token Index: 613

Text #18

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.8773. Min Act: -0.0000

Data Index: 1098546 (C4 (Web Text))

Max Activating Token Index: 527

Text #19

Max Range: 1.1239. Min Range: -1.1239

Max Act: 0.8722. Min Act: -0.0000

Data Index: 529705 (C4 (Web Text))

Max Activating Token Index: 875