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

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

Neuron 2509 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.3540. Min Act: -0.0001

Data Index: 575777 (C4 (Web Text))

Max Activating Token Index: 786

Text #1

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.2382. Min Act: -0.0001

Data Index: 403428 (C4 (Web Text))

Max Activating Token Index: 831

Text #2

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.2808. Min Act: -0.0001

Data Index: 435073 (C4 (Web Text))

Max Activating Token Index: 63

Text #3

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.2074. Min Act: -0.0001

Data Index: 548345 (C4 (Web Text))

Max Activating Token Index: 546

Text #4

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.1749. Min Act: -0.0001

Data Index: 1005091 (C4 (Web Text))

Max Activating Token Index: 725

Text #5

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.0953. Min Act: -0.0001

Data Index: 527529 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.1725. Min Act: -0.0001

Data Index: 348557 (C4 (Web Text))

Max Activating Token Index: 658

Text #7

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.1750. Min Act: -0.0001

Data Index: 237435 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.1770. Min Act: -0.0001

Data Index: 477419 (C4 (Web Text))

Max Activating Token Index: 592

Text #9

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.2938. Min Act: -0.0001

Data Index: 256182 (C4 (Web Text))

Max Activating Token Index: 701

Text #10

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.1481. Min Act: -0.0001

Data Index: 391162 (C4 (Web Text))

Max Activating Token Index: 104

Text #11

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.0402. Min Act: -0.0001

Data Index: 759535 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.0933. Min Act: -0.0001

Data Index: 1338711 (C4 (Web Text))

Max Activating Token Index: 812

Text #13

Max Range: 1.3540. Min Range: -1.3540

Max Act: 0.9932. Min Act: -0.0001

Data Index: 785591 (C4 (Web Text))

Max Activating Token Index: 822

Text #14

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.0983. Min Act: -0.0001

Data Index: 1083660 (C4 (Web Text))

Max Activating Token Index: 498

Text #15

Max Range: 1.3540. Min Range: -1.3540

Max Act: 0.9523. Min Act: -0.0001

Data Index: 970275 (C4 (Web Text))

Max Activating Token Index: 742

Text #16

Max Range: 1.3540. Min Range: -1.3540

Max Act: 0.9822. Min Act: -0.0001

Data Index: 683065 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.1291. Min Act: -0.0001

Data Index: 252814 (C4 (Web Text))

Max Activating Token Index: 700

Text #18

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.0298. Min Act: -0.0001

Data Index: 763604 (C4 (Web Text))

Max Activating Token Index: 416

Text #19

Max Range: 1.3540. Min Range: -1.3540

Max Act: 1.0744. Min Act: -0.0001

Data Index: 202640 (C4 (Web Text))

Max Activating Token Index: 451