Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 239 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.4122. Min Act: -0.0001

Data Index: 1634045 (Python Code)

Max Activating Token Index: 872

Text #1

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.4494. Min Act: -0.0001

Data Index: 1647227 (Python Code)

Max Activating Token Index: 588

Text #2

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.3017. Min Act: -0.0001

Data Index: 1499592 (Python Code)

Max Activating Token Index: 881

Text #3

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.3669. Min Act: -0.0001

Data Index: 1362486 (Python Code)

Max Activating Token Index: 938

Text #4

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.3383. Min Act: -0.0001

Data Index: 1552454 (Python Code)

Max Activating Token Index: 616

Text #5

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2954. Min Act: -0.0001

Data Index: 1566995 (Python Code)

Max Activating Token Index: 699

Text #6

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2873. Min Act: -0.0001

Data Index: 1565176 (Python Code)

Max Activating Token Index: 515

Text #7

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.3361. Min Act: -0.0001

Data Index: 1382409 (Python Code)

Max Activating Token Index: 992

Text #8

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2283. Min Act: -0.0001

Data Index: 1629828 (Python Code)

Max Activating Token Index: 165

Text #9

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.1726. Min Act: -0.0001

Data Index: 1469015 (Python Code)

Max Activating Token Index: 894

Text #10

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2384. Min Act: -0.0001

Data Index: 1505680 (Python Code)

Max Activating Token Index: 501

Text #11

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.1599. Min Act: -0.0001

Data Index: 1435238 (Python Code)

Max Activating Token Index: 57

Text #12

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2228. Min Act: -0.0001

Data Index: 1551432 (Python Code)

Max Activating Token Index: 726

Text #13

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2023. Min Act: -0.0001

Data Index: 1431820 (Python Code)

Max Activating Token Index: 792

Text #14

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.1233. Min Act: -0.0001

Data Index: 1529154 (Python Code)

Max Activating Token Index: 950

Text #15

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.2797. Min Act: -0.0001

Data Index: 1360343 (Python Code)

Max Activating Token Index: 791

Text #16

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.1698. Min Act: -0.0001

Data Index: 1606775 (Python Code)

Max Activating Token Index: 813

Text #17

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.1400. Min Act: -0.0001

Data Index: 1492405 (Python Code)

Max Activating Token Index: 333

Text #18

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.1727. Min Act: -0.0001

Data Index: 1431111 (Python Code)

Max Activating Token Index: 759

Text #19

Max Range: 1.4494. Min Range: -1.4494

Max Act: 1.0870. Min Act: -0.0001

Data Index: 1543633 (Python Code)

Max Activating Token Index: 912