Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 2001 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0989. Min Act: -0.0004

Data Index: 112254 (C4 (Web Text))

Max Activating Token Index: 1002

Text #1

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0812. Min Act: -0.0004

Data Index: 8239 (C4 (Web Text))

Max Activating Token Index: 308

Text #2

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0761. Min Act: -0.0004

Data Index: 363468 (C4 (Web Text))

Max Activating Token Index: 355

Text #3

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0766. Min Act: -0.0004

Data Index: 7421 (C4 (Web Text))

Max Activating Token Index: 395

Text #4

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0668. Min Act: -0.0004

Data Index: 366405 (C4 (Web Text))

Max Activating Token Index: 510

Text #5

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0666. Min Act: -0.0004

Data Index: 23752 (C4 (Web Text))

Max Activating Token Index: 401

Text #6

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0656. Min Act: -0.0004

Data Index: 1119903 (C4 (Web Text))

Max Activating Token Index: 622

Text #7

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0632. Min Act: -0.0004

Data Index: 1168139 (C4 (Web Text))

Max Activating Token Index: 519

Text #8

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0674. Min Act: -0.0004

Data Index: 1317938 (C4 (Web Text))

Max Activating Token Index: 946

Text #9

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0618. Min Act: -0.0004

Data Index: 884864 (C4 (Web Text))

Max Activating Token Index: 771

Text #10

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0661. Min Act: -0.0004

Data Index: 708894 (C4 (Web Text))

Max Activating Token Index: 750

Text #11

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0658. Min Act: -0.0004

Data Index: 343558 (C4 (Web Text))

Max Activating Token Index: 594

Text #12

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0653. Min Act: -0.0004

Data Index: 962187 (C4 (Web Text))

Max Activating Token Index: 727

Text #13

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0665. Min Act: -0.0004

Data Index: 223024 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0541. Min Act: -0.0004

Data Index: 1302811 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0637. Min Act: -0.0004

Data Index: 114103 (C4 (Web Text))

Max Activating Token Index: 791

Text #16

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0611. Min Act: -0.0004

Data Index: 15218 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0542. Min Act: -0.0004

Data Index: 65530 (C4 (Web Text))

Max Activating Token Index: 371

Text #18

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0611. Min Act: -0.0004

Data Index: 1063597 (C4 (Web Text))

Max Activating Token Index: 721

Text #19

Max Range: 0.0989. Min Range: -0.0989

Max Act: 0.0607. Min Act: -0.0004

Data Index: 209077 (C4 (Web Text))

Max Activating Token Index: 326