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

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

Neuron 2661 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: 1.8617. Min Range: -1.8617

Max Act: 1.8617. Min Act: -0.0000

Data Index: 396354 (C4 (Web Text))

Max Activating Token Index: 884

Text #1

Max Range: 1.8617. Min Range: -1.8617

Max Act: 1.4282. Min Act: -0.0000

Data Index: 36198 (C4 (Web Text))

Max Activating Token Index: 1000

Text #2

Max Range: 1.8617. Min Range: -1.8617

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1173344 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 1.8617. Min Range: -1.8617

Max Act: 1.1494. Min Act: -0.0000

Data Index: 258288 (C4 (Web Text))

Max Activating Token Index: 393

Text #4

Max Range: 1.8617. Min Range: -1.8617

Max Act: 1.1736. Min Act: -0.0000

Data Index: 981969 (C4 (Web Text))

Max Activating Token Index: 372

Text #5

Max Range: 1.8617. Min Range: -1.8617

Max Act: 1.1666. Min Act: -0.0000

Data Index: 532502 (C4 (Web Text))

Max Activating Token Index: 420

Text #6

Max Range: 1.8617. Min Range: -1.8617

Max Act: 1.1499. Min Act: -0.0000

Data Index: 309953 (C4 (Web Text))

Max Activating Token Index: 774

Text #7

Max Range: 1.8617. Min Range: -1.8617

Max Act: 1.1218. Min Act: 0.0000

Data Index: 112869 (C4 (Web Text))

Max Activating Token Index: 133

Text #8

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.9990. Min Act: -0.0000

Data Index: 721088 (C4 (Web Text))

Max Activating Token Index: 744

Text #9

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.9915. Min Act: 0.0000

Data Index: 754236 (C4 (Web Text))

Max Activating Token Index: 633

Text #10

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.9811. Min Act: -0.0000

Data Index: 31867 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.9769. Min Act: -0.0000

Data Index: 387652 (C4 (Web Text))

Max Activating Token Index: 193

Text #12

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.8941. Min Act: -0.0000

Data Index: 1050301 (C4 (Web Text))

Max Activating Token Index: 491

Text #13

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.8304. Min Act: 0.0001

Data Index: 1291697 (C4 (Web Text))

Max Activating Token Index: 794

Text #14

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.9248. Min Act: 0.0001

Data Index: 1011264 (C4 (Web Text))

Max Activating Token Index: 109

Text #15

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.8540. Min Act: -0.0000

Data Index: 317890 (C4 (Web Text))

Max Activating Token Index: 674

Text #16

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.8722. Min Act: -0.0000

Data Index: 338473 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.8577. Min Act: 0.0000

Data Index: 1097539 (C4 (Web Text))

Max Activating Token Index: 63

Text #18

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.8494. Min Act: -0.0000

Data Index: 854293 (C4 (Web Text))

Max Activating Token Index: 437

Text #19

Max Range: 1.8617. Min Range: -1.8617

Max Act: 0.8845. Min Act: -0.0000

Data Index: 552187 (C4 (Web Text))

Max Activating Token Index: 400