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

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

Neuron 146 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.6078. Min Act: -0.0000

Data Index: 513595 (C4 (Web Text))

Max Activating Token Index: 573

Text #1

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.3854. Min Act: -0.0000

Data Index: 662566 (C4 (Web Text))

Max Activating Token Index: 882

Text #2

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.3597. Min Act: -0.0000

Data Index: 158532 (C4 (Web Text))

Max Activating Token Index: 592

Text #3

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.3088. Min Act: -0.0000

Data Index: 443444 (C4 (Web Text))

Max Activating Token Index: 374

Text #4

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.3173. Min Act: -0.0000

Data Index: 5619 (C4 (Web Text))

Max Activating Token Index: 976

Text #5

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1917. Min Act: -0.0000

Data Index: 1460735 (Python Code)

Max Activating Token Index: 24

Text #6

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1661. Min Act: -0.0000

Data Index: 1127832 (C4 (Web Text))

Max Activating Token Index: 104

Text #7

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.2283. Min Act: -0.0000

Data Index: 1558842 (Python Code)

Max Activating Token Index: 859

Text #8

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1655. Min Act: -0.0000

Data Index: 1186158 (C4 (Web Text))

Max Activating Token Index: 491

Text #9

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1452. Min Act: -0.0000

Data Index: 1543881 (Python Code)

Max Activating Token Index: 270

Text #10

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0746. Min Act: -0.0000

Data Index: 1552779 (Python Code)

Max Activating Token Index: 117

Text #11

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.1006. Min Act: -0.0000

Data Index: 201702 (C4 (Web Text))

Max Activating Token Index: 284

Text #12

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0743. Min Act: -0.0000

Data Index: 1511709 (Python Code)

Max Activating Token Index: 593

Text #13

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.9492. Min Act: -0.0000

Data Index: 1371770 (Python Code)

Max Activating Token Index: 737

Text #14

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.9682. Min Act: -0.0000

Data Index: 1341642 (C4 (Web Text))

Max Activating Token Index: 294

Text #15

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0189. Min Act: -0.0000

Data Index: 24253 (C4 (Web Text))

Max Activating Token Index: 50

Text #16

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.9841. Min Act: -0.0000

Data Index: 424170 (C4 (Web Text))

Max Activating Token Index: 131

Text #17

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.9074. Min Act: -0.0000

Data Index: 643727 (C4 (Web Text))

Max Activating Token Index: 840

Text #18

Max Range: 1.6078. Min Range: -1.6078

Max Act: 0.8958. Min Act: -0.0000

Data Index: 1479113 (Python Code)

Max Activating Token Index: 728

Text #19

Max Range: 1.6078. Min Range: -1.6078

Max Act: 1.0381. Min Act: -0.0000

Data Index: 75142 (C4 (Web Text))

Max Activating Token Index: 923