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

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

Neuron 3716 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.3667. Min Act: 0.0000

Data Index: 930934 (C4 (Web Text))

Max Activating Token Index: 541

Text #1

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0493. Min Act: 0.0000

Data Index: 776872 (C4 (Web Text))

Max Activating Token Index: 354

Text #2

Max Range: 1.3667. Min Range: -1.3667

Max Act: 1.0484. Min Act: -0.0000

Data Index: 1219567 (C4 (Web Text))

Max Activating Token Index: 924

Text #3

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9775. Min Act: 0.0000

Data Index: 155978 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9806. Min Act: -0.0000

Data Index: 692739 (C4 (Web Text))

Max Activating Token Index: 508

Text #5

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9651. Min Act: -0.0000

Data Index: 360896 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8936. Min Act: -0.0000

Data Index: 1200369 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9492. Min Act: -0.0000

Data Index: 3816 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1251988 (C4 (Web Text))

Max Activating Token Index: 354

Text #9

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8911. Min Act: -0.0000

Data Index: 345423 (C4 (Web Text))

Max Activating Token Index: 40

Text #10

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8622. Min Act: -0.0000

Data Index: 685595 (C4 (Web Text))

Max Activating Token Index: 811

Text #11

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8547. Min Act: 0.0000

Data Index: 1166415 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8429. Min Act: -0.0000

Data Index: 644814 (C4 (Web Text))

Max Activating Token Index: 1006

Text #13

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7790. Min Act: -0.0000

Data Index: 905097 (C4 (Web Text))

Max Activating Token Index: 329

Text #14

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8276. Min Act: 0.0000

Data Index: 646091 (C4 (Web Text))

Max Activating Token Index: 602

Text #15

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7896. Min Act: 0.0000

Data Index: 174241 (C4 (Web Text))

Max Activating Token Index: 766

Text #16

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7705. Min Act: -0.0000

Data Index: 787363 (C4 (Web Text))

Max Activating Token Index: 693

Text #17

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8251. Min Act: -0.0000

Data Index: 148021 (C4 (Web Text))

Max Activating Token Index: 9

Text #18

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.8209. Min Act: 0.0000

Data Index: 557289 (C4 (Web Text))

Max Activating Token Index: 494

Text #19

Max Range: 1.3667. Min Range: -1.3667

Max Act: 0.7599. Min Act: -0.0000

Data Index: 719223 (C4 (Web Text))

Max Activating Token Index: 229