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

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

Neuron 4330 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.7170. Min Act: -0.0000

Data Index: 171229 (C4 (Web Text))

Max Activating Token Index: 865

Text #1

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5736. Min Act: -0.0000

Data Index: 480699 (C4 (Web Text))

Max Activating Token Index: 285

Text #2

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.6462. Min Act: -0.0000

Data Index: 180191 (C4 (Web Text))

Max Activating Token Index: 868

Text #3

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5674. Min Act: -0.0000

Data Index: 1340435 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5356. Min Act: -0.0000

Data Index: 1123232 (C4 (Web Text))

Max Activating Token Index: 331

Text #5

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5513. Min Act: -0.0000

Data Index: 1257036 (C4 (Web Text))

Max Activating Token Index: 633

Text #6

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5516. Min Act: -0.0000

Data Index: 351803 (C4 (Web Text))

Max Activating Token Index: 423

Text #7

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5114. Min Act: -0.0000

Data Index: 362451 (C4 (Web Text))

Max Activating Token Index: 870

Text #8

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5112. Min Act: -0.0000

Data Index: 1024515 (C4 (Web Text))

Max Activating Token Index: 66

Text #9

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5288. Min Act: -0.0000

Data Index: 142534 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5383. Min Act: -0.0000

Data Index: 737545 (C4 (Web Text))

Max Activating Token Index: 393

Text #11

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.5105. Min Act: -0.0000

Data Index: 407414 (C4 (Web Text))

Max Activating Token Index: 340

Text #12

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4567. Min Act: -0.0000

Data Index: 1011465 (C4 (Web Text))

Max Activating Token Index: 848

Text #13

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4850. Min Act: -0.0000

Data Index: 760929 (C4 (Web Text))

Max Activating Token Index: 597

Text #14

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.3714. Min Act: -0.0000

Data Index: 238720 (C4 (Web Text))

Max Activating Token Index: 696

Text #15

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4523. Min Act: -0.0000

Data Index: 76171 (C4 (Web Text))

Max Activating Token Index: 789

Text #16

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4528. Min Act: -0.0000

Data Index: 1201434 (C4 (Web Text))

Max Activating Token Index: 663

Text #17

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4314. Min Act: -0.0000

Data Index: 841020 (C4 (Web Text))

Max Activating Token Index: 687

Text #18

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4819. Min Act: -0.0000

Data Index: 227581 (C4 (Web Text))

Max Activating Token Index: 930

Text #19

Max Range: 0.7170. Min Range: -0.7170

Max Act: 0.4443. Min Act: -0.0001

Data Index: 307641 (C4 (Web Text))

Max Activating Token Index: 666