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

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

Neuron 5454 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.1748. Min Range: -2.1748

Max Act: 2.1748. Min Act: -0.0000

Data Index: 855112 (C4 (Web Text))

Max Activating Token Index: 306

Text #1

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.8453. Min Act: -0.0000

Data Index: 773095 (C4 (Web Text))

Max Activating Token Index: 692

Text #2

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.7616. Min Act: -0.0000

Data Index: 1150314 (C4 (Web Text))

Max Activating Token Index: 860

Text #3

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.7617. Min Act: -0.0000

Data Index: 1232143 (C4 (Web Text))

Max Activating Token Index: 715

Text #4

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.8008. Min Act: -0.0000

Data Index: 1530201 (Python Code)

Max Activating Token Index: 231

Text #5

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.6924. Min Act: -0.0000

Data Index: 641823 (C4 (Web Text))

Max Activating Token Index: 608

Text #6

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.6754. Min Act: -0.0000

Data Index: 1009771 (C4 (Web Text))

Max Activating Token Index: 684

Text #7

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.6708. Min Act: -0.0000

Data Index: 72255 (C4 (Web Text))

Max Activating Token Index: 139

Text #8

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.4804. Min Act: -0.0000

Data Index: 987331 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.6257. Min Act: -0.0000

Data Index: 1394237 (Python Code)

Max Activating Token Index: 563

Text #10

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.5035. Min Act: -0.0000

Data Index: 1188448 (C4 (Web Text))

Max Activating Token Index: 456

Text #11

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.5700. Min Act: -0.0000

Data Index: 1167293 (C4 (Web Text))

Max Activating Token Index: 1002

Text #12

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.5571. Min Act: 0.0001

Data Index: 1302742 (C4 (Web Text))

Max Activating Token Index: 147

Text #13

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.3831. Min Act: -0.0000

Data Index: 764105 (C4 (Web Text))

Max Activating Token Index: 62

Text #14

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.8372. Min Act: -0.0000

Data Index: 1006121 (C4 (Web Text))

Max Activating Token Index: 460

Text #15

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.4509. Min Act: 0.0001

Data Index: 649899 (C4 (Web Text))

Max Activating Token Index: 125

Text #16

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.3812. Min Act: -0.0000

Data Index: 243661 (C4 (Web Text))

Max Activating Token Index: 792

Text #17

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.5224. Min Act: -0.0000

Data Index: 161407 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.5113. Min Act: -0.0000

Data Index: 1551343 (Python Code)

Max Activating Token Index: 673

Text #19

Max Range: 2.1748. Min Range: -2.1748

Max Act: 1.4152. Min Act: 0.0000

Data Index: 19948 (C4 (Web Text))

Max Activating Token Index: 417