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

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

Neuron 1537 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4721. Min Act: -0.0001

Data Index: 676848 (C4 (Web Text))

Max Activating Token Index: 78

Text #1

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3729. Min Act: -0.0001

Data Index: 252774 (C4 (Web Text))

Max Activating Token Index: 258

Text #2

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4121. Min Act: -0.0001

Data Index: 380943 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.4001. Min Act: -0.0001

Data Index: 1334726 (C4 (Web Text))

Max Activating Token Index: 204

Text #4

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3876. Min Act: -0.0001

Data Index: 75903 (C4 (Web Text))

Max Activating Token Index: 1017

Text #5

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3764. Min Act: -0.0001

Data Index: 828224 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3778. Min Act: -0.0001

Data Index: 776338 (C4 (Web Text))

Max Activating Token Index: 957

Text #7

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3449. Min Act: -0.0001

Data Index: 145390 (C4 (Web Text))

Max Activating Token Index: 34

Text #8

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3468. Min Act: -0.0001

Data Index: 647867 (C4 (Web Text))

Max Activating Token Index: 238

Text #9

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3088. Min Act: -0.0001

Data Index: 254479 (C4 (Web Text))

Max Activating Token Index: 143

Text #10

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3687. Min Act: -0.0001

Data Index: 524993 (C4 (Web Text))

Max Activating Token Index: 808

Text #11

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3516. Min Act: -0.0001

Data Index: 280295 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3420. Min Act: -0.0001

Data Index: 602869 (C4 (Web Text))

Max Activating Token Index: 492

Text #13

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3881. Min Act: -0.0001

Data Index: 130320 (C4 (Web Text))

Max Activating Token Index: 819

Text #14

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3481. Min Act: -0.0001

Data Index: 1211139 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3457. Min Act: -0.0001

Data Index: 445264 (C4 (Web Text))

Max Activating Token Index: 451

Text #16

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3466. Min Act: -0.0001

Data Index: 126987 (C4 (Web Text))

Max Activating Token Index: 517

Text #17

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3444. Min Act: -0.0001

Data Index: 929344 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3618. Min Act: -0.0001

Data Index: 787143 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 0.4721. Min Range: -0.4721

Max Act: 0.3517. Min Act: -0.0001

Data Index: 1215007 (C4 (Web Text))

Max Activating Token Index: 334