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

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

Neuron 1907 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0344. Min Range: -1.0344

Max Act: 1.0344. Min Act: -0.0001

Data Index: 1142239 (C4 (Web Text))

Max Activating Token Index: 797

Text #1

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.8788. Min Act: -0.0001

Data Index: 977200 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.8663. Min Act: -0.0001

Data Index: 230027 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7670. Min Act: -0.0001

Data Index: 1310530 (C4 (Web Text))

Max Activating Token Index: 705

Text #4

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.8033. Min Act: -0.0001

Data Index: 670439 (C4 (Web Text))

Max Activating Token Index: 421

Text #5

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7991. Min Act: -0.0001

Data Index: 196718 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7651. Min Act: -0.0001

Data Index: 771832 (C4 (Web Text))

Max Activating Token Index: 734

Text #7

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7348. Min Act: -0.0001

Data Index: 400540 (C4 (Web Text))

Max Activating Token Index: 238

Text #8

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.8094. Min Act: -0.0001

Data Index: 613850 (C4 (Web Text))

Max Activating Token Index: 813

Text #9

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.8037. Min Act: -0.0001

Data Index: 154978 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7748. Min Act: -0.0001

Data Index: 1235611 (C4 (Web Text))

Max Activating Token Index: 695

Text #11

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7998. Min Act: -0.0001

Data Index: 1027446 (C4 (Web Text))

Max Activating Token Index: 458

Text #12

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7640. Min Act: -0.0001

Data Index: 147428 (C4 (Web Text))

Max Activating Token Index: 78

Text #13

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7821. Min Act: -0.0001

Data Index: 120350 (C4 (Web Text))

Max Activating Token Index: 220

Text #14

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7865. Min Act: -0.0001

Data Index: 10250 (C4 (Web Text))

Max Activating Token Index: 766

Text #15

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7276. Min Act: -0.0001

Data Index: 1226722 (C4 (Web Text))

Max Activating Token Index: 812

Text #16

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7548. Min Act: -0.0001

Data Index: 1514119 (Python Code)

Max Activating Token Index: 459

Text #17

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7525. Min Act: -0.0001

Data Index: 1254524 (C4 (Web Text))

Max Activating Token Index: 598

Text #18

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.7674. Min Act: -0.0001

Data Index: 1269631 (C4 (Web Text))

Max Activating Token Index: 378

Text #19

Max Range: 1.0344. Min Range: -1.0344

Max Act: 0.6950. Min Act: -0.0001

Data Index: 407568 (C4 (Web Text))

Max Activating Token Index: 114