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

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

Neuron 6128 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0753. Min Range: -1.0753

Max Act: 1.0753. Min Act: -0.0000

Data Index: 1431702 (Python Code)

Max Activating Token Index: 823

Text #1

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.8513. Min Act: -0.0000

Data Index: 791108 (C4 (Web Text))

Max Activating Token Index: 969

Text #2

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.7616. Min Act: -0.0000

Data Index: 1537871 (Python Code)

Max Activating Token Index: 150

Text #3

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.7502. Min Act: -0.0000

Data Index: 1022853 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6693. Min Act: -0.0000

Data Index: 213093 (C4 (Web Text))

Max Activating Token Index: 777

Text #5

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.7097. Min Act: -0.0000

Data Index: 184532 (C4 (Web Text))

Max Activating Token Index: 600

Text #6

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6683. Min Act: -0.0000

Data Index: 783042 (C4 (Web Text))

Max Activating Token Index: 213

Text #7

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6563. Min Act: -0.0000

Data Index: 275059 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6720. Min Act: -0.0000

Data Index: 1226189 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6954. Min Act: -0.0000

Data Index: 885325 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6825. Min Act: -0.0000

Data Index: 434164 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6389. Min Act: -0.0000

Data Index: 980556 (C4 (Web Text))

Max Activating Token Index: 430

Text #12

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6294. Min Act: -0.0000

Data Index: 1555914 (Python Code)

Max Activating Token Index: 836

Text #13

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6758. Min Act: -0.0000

Data Index: 802460 (C4 (Web Text))

Max Activating Token Index: 857

Text #14

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6653. Min Act: -0.0000

Data Index: 1455545 (Python Code)

Max Activating Token Index: 949

Text #15

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.5772. Min Act: -0.0000

Data Index: 737141 (C4 (Web Text))

Max Activating Token Index: 862

Text #16

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6458. Min Act: -0.0000

Data Index: 637197 (C4 (Web Text))

Max Activating Token Index: 766

Text #17

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6016. Min Act: -0.0000

Data Index: 1361278 (Python Code)

Max Activating Token Index: 786

Text #18

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.5842. Min Act: -0.0000

Data Index: 985521 (C4 (Web Text))

Max Activating Token Index: 237

Text #19

Max Range: 1.0753. Min Range: -1.0753

Max Act: 0.6013. Min Act: -0.0000

Data Index: 889109 (C4 (Web Text))

Max Activating Token Index: 935