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

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

Neuron 1906 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.4349. Min Range: -4.4349

Max Act: 4.3070. Min Act: -0.0000

Data Index: 1044886 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 4.4349. Min Range: -4.4349

Max Act: 4.4349. Min Act: -0.0000

Data Index: 596868 (C4 (Web Text))

Max Activating Token Index: 995

Text #2

Max Range: 4.4349. Min Range: -4.4349

Max Act: 4.4087. Min Act: -0.0000

Data Index: 14881 (C4 (Web Text))

Max Activating Token Index: 329

Text #3

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.9440. Min Act: -0.0000

Data Index: 653053 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 4.4349. Min Range: -4.4349

Max Act: 4.0050. Min Act: -0.0000

Data Index: 1042415 (C4 (Web Text))

Max Activating Token Index: 197

Text #5

Max Range: 4.4349. Min Range: -4.4349

Max Act: 4.1079. Min Act: -0.0000

Data Index: 253151 (C4 (Web Text))

Max Activating Token Index: 843

Text #6

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.7238. Min Act: -0.0000

Data Index: 1205542 (C4 (Web Text))

Max Activating Token Index: 649

Text #7

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.8688. Min Act: -0.0000

Data Index: 297928 (C4 (Web Text))

Max Activating Token Index: 913

Text #8

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.5478. Min Act: -0.0000

Data Index: 1057516 (C4 (Web Text))

Max Activating Token Index: 492

Text #9

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.5526. Min Act: -0.0000

Data Index: 686735 (C4 (Web Text))

Max Activating Token Index: 224

Text #10

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.6351. Min Act: -0.0000

Data Index: 699977 (C4 (Web Text))

Max Activating Token Index: 36

Text #11

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.7900. Min Act: -0.0000

Data Index: 557002 (C4 (Web Text))

Max Activating Token Index: 648

Text #12

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.4846. Min Act: -0.0000

Data Index: 563636 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.6153. Min Act: -0.0000

Data Index: 970649 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.4420. Min Act: -0.0000

Data Index: 328734 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.7147. Min Act: -0.0000

Data Index: 946757 (C4 (Web Text))

Max Activating Token Index: 904

Text #16

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.6755. Min Act: -0.0000

Data Index: 1031051 (C4 (Web Text))

Max Activating Token Index: 991

Text #17

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.4720. Min Act: -0.0000

Data Index: 48185 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.8070. Min Act: -0.0000

Data Index: 973582 (C4 (Web Text))

Max Activating Token Index: 92

Text #19

Max Range: 4.4349. Min Range: -4.4349

Max Act: 3.7918. Min Act: -0.0000

Data Index: 83576 (C4 (Web Text))

Max Activating Token Index: 421