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

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

Neuron 1575 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: 0.0964. Min Range: -0.0964

Max Act: 0.0964. Min Act: -0.0001

Data Index: 350680 (C4 (Web Text))

Max Activating Token Index: 775

Text #1

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0906. Min Act: -0.0001

Data Index: 429411 (C4 (Web Text))

Max Activating Token Index: 761

Text #2

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0881. Min Act: -0.0001

Data Index: 1171607 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0811. Min Act: -0.0001

Data Index: 96245 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0832. Min Act: -0.0001

Data Index: 532392 (C4 (Web Text))

Max Activating Token Index: 570

Text #5

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0821. Min Act: -0.0001

Data Index: 557990 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0782. Min Act: -0.0001

Data Index: 827628 (C4 (Web Text))

Max Activating Token Index: 430

Text #7

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0770. Min Act: -0.0001

Data Index: 115810 (C4 (Web Text))

Max Activating Token Index: 795

Text #8

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0763. Min Act: -0.0001

Data Index: 1293581 (C4 (Web Text))

Max Activating Token Index: 896

Text #9

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0737. Min Act: -0.0001

Data Index: 327179 (C4 (Web Text))

Max Activating Token Index: 836

Text #10

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0707. Min Act: -0.0001

Data Index: 1261765 (C4 (Web Text))

Max Activating Token Index: 894

Text #11

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0637. Min Act: -0.0001

Data Index: 833058 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0687. Min Act: -0.0001

Data Index: 612647 (C4 (Web Text))

Max Activating Token Index: 499

Text #13

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0709. Min Act: -0.0001

Data Index: 854391 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0734. Min Act: -0.0001

Data Index: 664687 (C4 (Web Text))

Max Activating Token Index: 719

Text #15

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0747. Min Act: -0.0001

Data Index: 352789 (C4 (Web Text))

Max Activating Token Index: 311

Text #16

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0723. Min Act: -0.0001

Data Index: 1273814 (C4 (Web Text))

Max Activating Token Index: 492

Text #17

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0726. Min Act: -0.0001

Data Index: 661158 (C4 (Web Text))

Max Activating Token Index: 37

Text #18

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0724. Min Act: -0.0001

Data Index: 494094 (C4 (Web Text))

Max Activating Token Index: 697

Text #19

Max Range: 0.0964. Min Range: -0.0964

Max Act: 0.0722. Min Act: -0.0001

Data Index: 1117068 (C4 (Web Text))

Max Activating Token Index: 421