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

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

Neuron 4784 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: 2.0287. Min Range: -2.0287

Max Act: 2.0287. Min Act: -0.0000

Data Index: 871789 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.6727. Min Act: -0.0000

Data Index: 60180 (C4 (Web Text))

Max Activating Token Index: 146

Text #2

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.6028. Min Act: -0.0000

Data Index: 665664 (C4 (Web Text))

Max Activating Token Index: 622

Text #3

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.1935. Min Act: -0.0000

Data Index: 977200 (C4 (Web Text))

Max Activating Token Index: 559

Text #4

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.1794. Min Act: 0.0000

Data Index: 1165799 (C4 (Web Text))

Max Activating Token Index: 774

Text #5

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.1378. Min Act: -0.0000

Data Index: 329400 (C4 (Web Text))

Max Activating Token Index: 267

Text #6

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.0536. Min Act: 0.0000

Data Index: 1048430 (C4 (Web Text))

Max Activating Token Index: 86

Text #7

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.0343. Min Act: -0.0000

Data Index: 789750 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.0387. Min Act: 0.0001

Data Index: 716273 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 2.0287. Min Range: -2.0287

Max Act: 1.0140. Min Act: -0.0000

Data Index: 945996 (C4 (Web Text))

Max Activating Token Index: 952

Text #10

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.9890. Min Act: 0.0000

Data Index: 547244 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.9197. Min Act: 0.0001

Data Index: 536088 (C4 (Web Text))

Max Activating Token Index: 305

Text #12

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.9163. Min Act: -0.0000

Data Index: 1182918 (C4 (Web Text))

Max Activating Token Index: 793

Text #13

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.9403. Min Act: -0.0000

Data Index: 1053128 (C4 (Web Text))

Max Activating Token Index: 496

Text #14

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.9643. Min Act: -0.0000

Data Index: 175009 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1074024 (C4 (Web Text))

Max Activating Token Index: 869

Text #16

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.8855. Min Act: -0.0000

Data Index: 71702 (C4 (Web Text))

Max Activating Token Index: 549

Text #17

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.8920. Min Act: -0.0000

Data Index: 877546 (C4 (Web Text))

Max Activating Token Index: 729

Text #18

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.8696. Min Act: -0.0000

Data Index: 276099 (C4 (Web Text))

Max Activating Token Index: 687

Text #19

Max Range: 2.0287. Min Range: -2.0287

Max Act: 0.7943. Min Act: -0.0000

Data Index: 1170969 (C4 (Web Text))

Max Activating Token Index: 123