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

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

Neuron 2443 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.1081. Min Act: -0.0003

Data Index: 175607 (C4 (Web Text))

Max Activating Token Index: 265

Text #1

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0878. Min Act: -0.0003

Data Index: 1308583 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0821. Min Act: -0.0003

Data Index: 337601 (C4 (Web Text))

Max Activating Token Index: 14

Text #3

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0759. Min Act: -0.0003

Data Index: 1217971 (C4 (Web Text))

Max Activating Token Index: 480

Text #4

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0784. Min Act: -0.0003

Data Index: 1002782 (C4 (Web Text))

Max Activating Token Index: 441

Text #5

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0716. Min Act: -0.0003

Data Index: 11313 (C4 (Web Text))

Max Activating Token Index: 417

Text #6

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0734. Min Act: -0.0003

Data Index: 1067306 (C4 (Web Text))

Max Activating Token Index: 606

Text #7

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0711. Min Act: -0.0003

Data Index: 157582 (C4 (Web Text))

Max Activating Token Index: 712

Text #8

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0641. Min Act: -0.0003

Data Index: 361761 (C4 (Web Text))

Max Activating Token Index: 539

Text #9

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0708. Min Act: -0.0003

Data Index: 720639 (C4 (Web Text))

Max Activating Token Index: 320

Text #10

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0738. Min Act: -0.0003

Data Index: 558066 (C4 (Web Text))

Max Activating Token Index: 502

Text #11

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0731. Min Act: -0.0003

Data Index: 413200 (C4 (Web Text))

Max Activating Token Index: 915

Text #12

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0649. Min Act: -0.0003

Data Index: 809006 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0679. Min Act: -0.0003

Data Index: 844642 (C4 (Web Text))

Max Activating Token Index: 697

Text #14

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0666. Min Act: -0.0003

Data Index: 332506 (C4 (Web Text))

Max Activating Token Index: 266

Text #15

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0685. Min Act: -0.0003

Data Index: 251665 (C4 (Web Text))

Max Activating Token Index: 460

Text #16

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0706. Min Act: -0.0003

Data Index: 304233 (C4 (Web Text))

Max Activating Token Index: 273

Text #17

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0656. Min Act: -0.0003

Data Index: 698083 (C4 (Web Text))

Max Activating Token Index: 337

Text #18

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0676. Min Act: -0.0003

Data Index: 1131894 (C4 (Web Text))

Max Activating Token Index: 474

Text #19

Max Range: 0.1081. Min Range: -0.1081

Max Act: 0.0701. Min Act: -0.0003

Data Index: 1257090 (C4 (Web Text))

Max Activating Token Index: 749