Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3777 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1229. Min Act: -0.0001

Data Index: 274076 (C4 (Web Text))

Max Activating Token Index: 489

Text #1

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1126. Min Act: -0.0001

Data Index: 101108 (C4 (Web Text))

Max Activating Token Index: 601

Text #2

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.1135. Min Act: -0.0001

Data Index: 1064649 (C4 (Web Text))

Max Activating Token Index: 620

Text #3

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0948. Min Act: -0.0001

Data Index: 1219081 (C4 (Web Text))

Max Activating Token Index: 506

Text #4

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1045930 (C4 (Web Text))

Max Activating Token Index: 587

Text #5

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0975. Min Act: -0.0001

Data Index: 993408 (C4 (Web Text))

Max Activating Token Index: 559

Text #6

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0845. Min Act: -0.0001

Data Index: 898048 (C4 (Web Text))

Max Activating Token Index: 527

Text #7

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0945. Min Act: -0.0001

Data Index: 892590 (C4 (Web Text))

Max Activating Token Index: 835

Text #8

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0845. Min Act: -0.0001

Data Index: 861545 (C4 (Web Text))

Max Activating Token Index: 432

Text #9

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0825. Min Act: -0.0001

Data Index: 1050294 (C4 (Web Text))

Max Activating Token Index: 561

Text #10

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0896. Min Act: -0.0001

Data Index: 1282523 (C4 (Web Text))

Max Activating Token Index: 798

Text #11

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0780. Min Act: -0.0001

Data Index: 1039755 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0795. Min Act: -0.0001

Data Index: 1626192 (Python Code)

Max Activating Token Index: 741

Text #13

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0836. Min Act: -0.0001

Data Index: 1108952 (C4 (Web Text))

Max Activating Token Index: 858

Text #14

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0819. Min Act: -0.0001

Data Index: 455874 (C4 (Web Text))

Max Activating Token Index: 385

Text #15

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0787. Min Act: -0.0001

Data Index: 725783 (C4 (Web Text))

Max Activating Token Index: 472

Text #16

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0809. Min Act: -0.0001

Data Index: 347159 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0804. Min Act: -0.0001

Data Index: 768716 (C4 (Web Text))

Max Activating Token Index: 510

Text #18

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0771. Min Act: -0.0001

Data Index: 170090 (C4 (Web Text))

Max Activating Token Index: 561

Text #19

Max Range: 0.1229. Min Range: -0.1229

Max Act: 0.0731. Min Act: -0.0001

Data Index: 894801 (C4 (Web Text))

Max Activating Token Index: 933