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

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

Neuron 3400 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.8658. Min Act: -0.0000

Data Index: 835829 (C4 (Web Text))

Max Activating Token Index: 671

Text #1

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.8525. Min Act: -0.0000

Data Index: 160400 (C4 (Web Text))

Max Activating Token Index: 272

Text #2

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.6063. Min Act: -0.0000

Data Index: 1221408 (C4 (Web Text))

Max Activating Token Index: 427

Text #3

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.5659. Min Act: -0.0000

Data Index: 1061568 (C4 (Web Text))

Max Activating Token Index: 403

Text #4

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.4446. Min Act: -0.0000

Data Index: 809831 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.5085. Min Act: -0.0000

Data Index: 534443 (C4 (Web Text))

Max Activating Token Index: 61

Text #6

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.4806. Min Act: -0.0000

Data Index: 220361 (C4 (Web Text))

Max Activating Token Index: 694

Text #7

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.1558. Min Act: -0.0000

Data Index: 621446 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.4366. Min Act: -0.0000

Data Index: 644244 (C4 (Web Text))

Max Activating Token Index: 796

Text #9

Max Range: 2.8658. Min Range: -2.8658

Max Act: 1.9134. Min Act: -0.0000

Data Index: 554214 (C4 (Web Text))

Max Activating Token Index: 832

Text #10

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.1561. Min Act: -0.0000

Data Index: 1073855 (C4 (Web Text))

Max Activating Token Index: 56

Text #11

Max Range: 2.8658. Min Range: -2.8658

Max Act: 1.9998. Min Act: -0.0000

Data Index: 178713 (C4 (Web Text))

Max Activating Token Index: 381

Text #12

Max Range: 2.8658. Min Range: -2.8658

Max Act: 1.9701. Min Act: -0.0000

Data Index: 787562 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 2.8658. Min Range: -2.8658

Max Act: 1.9692. Min Act: -0.0000

Data Index: 1153075 (C4 (Web Text))

Max Activating Token Index: 262

Text #14

Max Range: 2.8658. Min Range: -2.8658

Max Act: 1.9612. Min Act: -0.0000

Data Index: 295931 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.1824. Min Act: -0.0000

Data Index: 1183901 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.0510. Min Act: -0.0000

Data Index: 464820 (C4 (Web Text))

Max Activating Token Index: 64

Text #17

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.1466. Min Act: -0.0000

Data Index: 1108905 (C4 (Web Text))

Max Activating Token Index: 647

Text #18

Max Range: 2.8658. Min Range: -2.8658

Max Act: 2.0361. Min Act: -0.0000

Data Index: 290261 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 2.8658. Min Range: -2.8658

Max Act: 1.9133. Min Act: -0.0000

Data Index: 582863 (C4 (Web Text))

Max Activating Token Index: 61