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

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

Neuron 479 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.5702. Min Act: -0.0000

Data Index: 162847 (C4 (Web Text))

Max Activating Token Index: 382

Text #1

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4788. Min Act: -0.0000

Data Index: 10092 (C4 (Web Text))

Max Activating Token Index: 259

Text #2

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1316149 (C4 (Web Text))

Max Activating Token Index: 579

Text #3

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4649. Min Act: -0.0000

Data Index: 753421 (C4 (Web Text))

Max Activating Token Index: 285

Text #4

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.4196. Min Act: -0.0000

Data Index: 1238354 (C4 (Web Text))

Max Activating Token Index: 161

Text #5

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.3975. Min Act: -0.0000

Data Index: 773598 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.3513. Min Act: -0.0000

Data Index: 416967 (C4 (Web Text))

Max Activating Token Index: 812

Text #7

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.3512. Min Act: -0.0000

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 759

Text #8

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.3203. Min Act: -0.0000

Data Index: 898837 (C4 (Web Text))

Max Activating Token Index: 905

Text #9

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.3184. Min Act: -0.0000

Data Index: 294947 (C4 (Web Text))

Max Activating Token Index: 708

Text #10

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.3090. Min Act: -0.0000

Data Index: 725469 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2992. Min Act: -0.0000

Data Index: 190414 (C4 (Web Text))

Max Activating Token Index: 233

Text #12

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2751. Min Act: -0.0000

Data Index: 51371 (C4 (Web Text))

Max Activating Token Index: 1000

Text #13

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2904. Min Act: -0.0000

Data Index: 826432 (C4 (Web Text))

Max Activating Token Index: 186

Text #14

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2891. Min Act: -0.0000

Data Index: 228071 (C4 (Web Text))

Max Activating Token Index: 426

Text #15

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2929. Min Act: -0.0000

Data Index: 270497 (C4 (Web Text))

Max Activating Token Index: 951

Text #16

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2798. Min Act: -0.0000

Data Index: 503797 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2773. Min Act: -0.0000

Data Index: 336096 (C4 (Web Text))

Max Activating Token Index: 792

Text #18

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2820. Min Act: -0.0000

Data Index: 1076696 (C4 (Web Text))

Max Activating Token Index: 811

Text #19

Max Range: 0.5702. Min Range: -0.5702

Max Act: 0.2784. Min Act: -0.0000

Data Index: 377554 (C4 (Web Text))

Max Activating Token Index: 967