Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3275 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0701. Min Act: -0.0003

Data Index: 16631 (C4 (Web Text))

Max Activating Token Index: 860

Text #1

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0678. Min Act: -0.0002

Data Index: 433662 (C4 (Web Text))

Max Activating Token Index: 832

Text #2

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0642. Min Act: -0.0002

Data Index: 336053 (C4 (Web Text))

Max Activating Token Index: 389

Text #3

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0574. Min Act: -0.0003

Data Index: 156182 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0587. Min Act: -0.0003

Data Index: 247764 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0565. Min Act: -0.0002

Data Index: 378613 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0496. Min Act: -0.0002

Data Index: 435941 (C4 (Web Text))

Max Activating Token Index: 447

Text #7

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0475. Min Act: -0.0002

Data Index: 722270 (C4 (Web Text))

Max Activating Token Index: 143

Text #8

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0557. Min Act: -0.0002

Data Index: 564731 (C4 (Web Text))

Max Activating Token Index: 239

Text #9

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0575. Min Act: -0.0002

Data Index: 618445 (C4 (Web Text))

Max Activating Token Index: 925

Text #10

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0533. Min Act: -0.0002

Data Index: 636306 (C4 (Web Text))

Max Activating Token Index: 84

Text #11

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0531. Min Act: -0.0003

Data Index: 255767 (C4 (Web Text))

Max Activating Token Index: 415

Text #12

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0529. Min Act: -0.0002

Data Index: 457690 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0480. Min Act: -0.0002

Data Index: 302004 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0566. Min Act: -0.0002

Data Index: 369759 (C4 (Web Text))

Max Activating Token Index: 912

Text #15

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0485. Min Act: -0.0002

Data Index: 848736 (C4 (Web Text))

Max Activating Token Index: 807

Text #16

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0375. Min Act: -0.0002

Data Index: 476185 (C4 (Web Text))

Max Activating Token Index: 606

Text #17

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0556. Min Act: -0.0002

Data Index: 963424 (C4 (Web Text))

Max Activating Token Index: 428

Text #18

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0443. Min Act: -0.0002

Data Index: 741369 (C4 (Web Text))

Max Activating Token Index: 784

Text #19

Max Range: 0.0701. Min Range: -0.0701

Max Act: 0.0505. Min Act: -0.0003

Data Index: 233403 (C4 (Web Text))

Max Activating Token Index: 956