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

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

Neuron 2219 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.9668. Min Act: -0.0000

Data Index: 30846 (C4 (Web Text))

Max Activating Token Index: 892

Text #1

Max Range: 3.0703. Min Range: -3.0703

Max Act: 3.0703. Min Act: -0.0000

Data Index: 365163 (C4 (Web Text))

Max Activating Token Index: 100

Text #2

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.6968. Min Act: -0.0000

Data Index: 846813 (C4 (Web Text))

Max Activating Token Index: 640

Text #3

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.5860. Min Act: -0.0000

Data Index: 809945 (C4 (Web Text))

Max Activating Token Index: 36

Text #4

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.5183. Min Act: -0.0000

Data Index: 425379 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.3359. Min Act: -0.0000

Data Index: 1127454 (C4 (Web Text))

Max Activating Token Index: 467

Text #6

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.1522. Min Act: -0.0000

Data Index: 1049422 (C4 (Web Text))

Max Activating Token Index: 22

Text #7

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.1368. Min Act: -0.0000

Data Index: 686029 (C4 (Web Text))

Max Activating Token Index: 747

Text #8

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.2592. Min Act: -0.0000

Data Index: 365238 (C4 (Web Text))

Max Activating Token Index: 625

Text #9

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.2367. Min Act: -0.0000

Data Index: 710401 (C4 (Web Text))

Max Activating Token Index: 817

Text #10

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.0940. Min Act: -0.0000

Data Index: 421671 (C4 (Web Text))

Max Activating Token Index: 286

Text #11

Max Range: 3.0703. Min Range: -3.0703

Max Act: 1.9660. Min Act: -0.0000

Data Index: 1126012 (C4 (Web Text))

Max Activating Token Index: 333

Text #12

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.0893. Min Act: -0.0000

Data Index: 398690 (C4 (Web Text))

Max Activating Token Index: 49

Text #13

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.1883. Min Act: -0.0000

Data Index: 1124486 (C4 (Web Text))

Max Activating Token Index: 237

Text #14

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.0664. Min Act: -0.0000

Data Index: 881392 (C4 (Web Text))

Max Activating Token Index: 938

Text #15

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.1881. Min Act: -0.0000

Data Index: 491150 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.0104. Min Act: -0.0000

Data Index: 442015 (C4 (Web Text))

Max Activating Token Index: 392

Text #17

Max Range: 3.0703. Min Range: -3.0703

Max Act: 1.9784. Min Act: -0.0000

Data Index: 745345 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 3.0703. Min Range: -3.0703

Max Act: 2.0210. Min Act: -0.0000

Data Index: 1087794 (C4 (Web Text))

Max Activating Token Index: 270

Text #19

Max Range: 3.0703. Min Range: -3.0703

Max Act: 1.9999. Min Act: -0.0000

Data Index: 1183388 (C4 (Web Text))

Max Activating Token Index: 835