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

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

Neuron 2580 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.4908. Min Act: -0.0000

Data Index: 1250760 (C4 (Web Text))

Max Activating Token Index: 383

Text #1

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.4198. Min Act: -0.0000

Data Index: 878229 (C4 (Web Text))

Max Activating Token Index: 325

Text #2

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.4926. Min Act: -0.0000

Data Index: 179597 (C4 (Web Text))

Max Activating Token Index: 490

Text #3

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.0292. Min Act: -0.0000

Data Index: 752699 (C4 (Web Text))

Max Activating Token Index: 828

Text #4

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.0816. Min Act: -0.0000

Data Index: 1144394 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.0000. Min Act: -0.0000

Data Index: 1172635 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.0462. Min Act: -0.0000

Data Index: 180695 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.0293. Min Act: -0.0000

Data Index: 821476 (C4 (Web Text))

Max Activating Token Index: 850

Text #8

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.0020. Min Act: -0.0000

Data Index: 780331 (C4 (Web Text))

Max Activating Token Index: 644

Text #9

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1202163 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9687. Min Act: -0.0000

Data Index: 466865 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.8895. Min Act: -0.0000

Data Index: 737874 (C4 (Web Text))

Max Activating Token Index: 523

Text #12

Max Range: 1.4926. Min Range: -1.4926

Max Act: 1.0075. Min Act: -0.0000

Data Index: 679188 (C4 (Web Text))

Max Activating Token Index: 250

Text #13

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9115. Min Act: -0.0000

Data Index: 1178894 (C4 (Web Text))

Max Activating Token Index: 71

Text #14

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9104. Min Act: -0.0000

Data Index: 491749 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9294. Min Act: -0.0000

Data Index: 112538 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9314. Min Act: -0.0000

Data Index: 1200059 (C4 (Web Text))

Max Activating Token Index: 167

Text #17

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9250. Min Act: -0.0000

Data Index: 410173 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9179. Min Act: -0.0000

Data Index: 34853 (C4 (Web Text))

Max Activating Token Index: 689

Text #19

Max Range: 1.4926. Min Range: -1.4926

Max Act: 0.9752. Min Act: -0.0000

Data Index: 858625 (C4 (Web Text))

Max Activating Token Index: 719