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

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

Neuron 38 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2632. Min Act: -0.0001

Data Index: 1121270 (C4 (Web Text))

Max Activating Token Index: 756

Text #1

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2719. Min Act: -0.0001

Data Index: 168005 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2687. Min Act: -0.0001

Data Index: 1121864 (C4 (Web Text))

Max Activating Token Index: 695

Text #3

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2378. Min Act: -0.0001

Data Index: 451529 (C4 (Web Text))

Max Activating Token Index: 530

Text #4

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2255. Min Act: -0.0001

Data Index: 1016739 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2259. Min Act: -0.0001

Data Index: 246300 (C4 (Web Text))

Max Activating Token Index: 1014

Text #6

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2046. Min Act: -0.0001

Data Index: 270409 (C4 (Web Text))

Max Activating Token Index: 704

Text #7

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.2176. Min Act: -0.0001

Data Index: 1167120 (C4 (Web Text))

Max Activating Token Index: 473

Text #8

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1697. Min Act: -0.0001

Data Index: 581110 (C4 (Web Text))

Max Activating Token Index: 306

Text #9

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1858. Min Act: -0.0001

Data Index: 1189339 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1712. Min Act: -0.0001

Data Index: 606057 (C4 (Web Text))

Max Activating Token Index: 16

Text #11

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1652. Min Act: -0.0001

Data Index: 947283 (C4 (Web Text))

Max Activating Token Index: 382

Text #12

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1570. Min Act: -0.0001

Data Index: 474208 (C4 (Web Text))

Max Activating Token Index: 815

Text #13

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1512. Min Act: -0.0001

Data Index: 960633 (C4 (Web Text))

Max Activating Token Index: 106

Text #14

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1505. Min Act: -0.0001

Data Index: 74757 (C4 (Web Text))

Max Activating Token Index: 529

Text #15

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1594. Min Act: -0.0001

Data Index: 606381 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1524. Min Act: -0.0001

Data Index: 253972 (C4 (Web Text))

Max Activating Token Index: 789

Text #17

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1344. Min Act: -0.0001

Data Index: 762935 (C4 (Web Text))

Max Activating Token Index: 855

Text #18

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1490. Min Act: -0.0001

Data Index: 462148 (C4 (Web Text))

Max Activating Token Index: 188

Text #19

Max Range: 0.2719. Min Range: -0.2719

Max Act: 0.1367. Min Act: -0.0001

Data Index: 656981 (C4 (Web Text))

Max Activating Token Index: 524