Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 21 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1846. Min Act: -0.0001

Data Index: 1060141 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1850. Min Act: -0.0001

Data Index: 1080311 (C4 (Web Text))

Max Activating Token Index: 224

Text #2

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1645. Min Act: -0.0001

Data Index: 1154710 (C4 (Web Text))

Max Activating Token Index: 10

Text #3

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1694. Min Act: -0.0001

Data Index: 1223953 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1668. Min Act: -0.0001

Data Index: 1143075 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1707. Min Act: -0.0001

Data Index: 689785 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1616. Min Act: -0.0001

Data Index: 233235 (C4 (Web Text))

Max Activating Token Index: 133

Text #7

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1663. Min Act: -0.0001

Data Index: 5784 (C4 (Web Text))

Max Activating Token Index: 792

Text #8

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1671. Min Act: -0.0001

Data Index: 630121 (C4 (Web Text))

Max Activating Token Index: 786

Text #9

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1622. Min Act: -0.0001

Data Index: 631680 (C4 (Web Text))

Max Activating Token Index: 794

Text #10

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1593. Min Act: -0.0001

Data Index: 85502 (C4 (Web Text))

Max Activating Token Index: 468

Text #11

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1525. Min Act: -0.0001

Data Index: 430930 (C4 (Web Text))

Max Activating Token Index: 609

Text #12

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1542. Min Act: -0.0001

Data Index: 1125864 (C4 (Web Text))

Max Activating Token Index: 291

Text #13

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1489. Min Act: -0.0001

Data Index: 946208 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1629. Min Act: -0.0001

Data Index: 711568 (C4 (Web Text))

Max Activating Token Index: 945

Text #15

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1528. Min Act: -0.0001

Data Index: 920516 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1636. Min Act: -0.0001

Data Index: 902505 (C4 (Web Text))

Max Activating Token Index: 645

Text #17

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1537. Min Act: -0.0001

Data Index: 220585 (C4 (Web Text))

Max Activating Token Index: 156

Text #18

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1584. Min Act: -0.0001

Data Index: 608265 (C4 (Web Text))

Max Activating Token Index: 443

Text #19

Max Range: 0.1850. Min Range: -0.1850

Max Act: 0.1530. Min Act: -0.0001

Data Index: 707707 (C4 (Web Text))

Max Activating Token Index: 268