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

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

Neuron 4224 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: 0.2307. Min Range: -0.2307

Max Act: 0.2307. Min Act: -0.0001

Data Index: 133855 (C4 (Web Text))

Max Activating Token Index: 1022

Text #1

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2094. Min Act: -0.0001

Data Index: 317157 (C4 (Web Text))

Max Activating Token Index: 163

Text #2

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.2165. Min Act: -0.0001

Data Index: 747437 (C4 (Web Text))

Max Activating Token Index: 139

Text #3

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1965. Min Act: -0.0001

Data Index: 828483 (C4 (Web Text))

Max Activating Token Index: 314

Text #4

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1864. Min Act: -0.0001

Data Index: 158375 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1648. Min Act: -0.0001

Data Index: 635658 (C4 (Web Text))

Max Activating Token Index: 138

Text #6

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1676. Min Act: -0.0001

Data Index: 1312486 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1617. Min Act: -0.0001

Data Index: 1134779 (C4 (Web Text))

Max Activating Token Index: 702

Text #8

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1755. Min Act: -0.0001

Data Index: 67752 (C4 (Web Text))

Max Activating Token Index: 138

Text #9

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1697. Min Act: -0.0001

Data Index: 148498 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1613. Min Act: -0.0001

Data Index: 442677 (C4 (Web Text))

Max Activating Token Index: 748

Text #11

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1660. Min Act: -0.0001

Data Index: 283484 (C4 (Web Text))

Max Activating Token Index: 669

Text #12

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1523. Min Act: -0.0001

Data Index: 1259232 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1564. Min Act: -0.0001

Data Index: 752837 (C4 (Web Text))

Max Activating Token Index: 574

Text #14

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1539. Min Act: -0.0001

Data Index: 693637 (C4 (Web Text))

Max Activating Token Index: 174

Text #15

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1502. Min Act: -0.0001

Data Index: 314094 (C4 (Web Text))

Max Activating Token Index: 842

Text #16

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1445. Min Act: -0.0001

Data Index: 357880 (C4 (Web Text))

Max Activating Token Index: 717

Text #17

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1286378 (C4 (Web Text))

Max Activating Token Index: 435

Text #18

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1442. Min Act: -0.0001

Data Index: 786569 (C4 (Web Text))

Max Activating Token Index: 357

Text #19

Max Range: 0.2307. Min Range: -0.2307

Max Act: 0.1444. Min Act: -0.0001

Data Index: 640064 (C4 (Web Text))

Max Activating Token Index: 962