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

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

Neuron 4327 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.5959. Min Act: -0.0000

Data Index: 929343 (C4 (Web Text))

Max Activating Token Index: 385

Text #1

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.4602. Min Act: -0.0000

Data Index: 455893 (C4 (Web Text))

Max Activating Token Index: 143

Text #2

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.2261. Min Act: -0.0000

Data Index: 956028 (C4 (Web Text))

Max Activating Token Index: 737

Text #3

Max Range: 4.6776. Min Range: -4.6776

Max Act: 3.7838. Min Act: -0.0000

Data Index: 1224548 (C4 (Web Text))

Max Activating Token Index: 770

Text #4

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.6776. Min Act: -0.0000

Data Index: 631767 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.0036. Min Act: -0.0000

Data Index: 967646 (C4 (Web Text))

Max Activating Token Index: 806

Text #6

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.0055. Min Act: -0.0000

Data Index: 825808 (C4 (Web Text))

Max Activating Token Index: 443

Text #7

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.3096. Min Act: -0.0000

Data Index: 393792 (C4 (Web Text))

Max Activating Token Index: 914

Text #8

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.3451. Min Act: -0.0000

Data Index: 660425 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.6377. Min Act: -0.0000

Data Index: 368330 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.0648. Min Act: -0.0000

Data Index: 1047702 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.1336. Min Act: -0.0000

Data Index: 424393 (C4 (Web Text))

Max Activating Token Index: 979

Text #12

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.1332. Min Act: -0.0000

Data Index: 157034 (C4 (Web Text))

Max Activating Token Index: 683

Text #13

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.4064. Min Act: -0.0000

Data Index: 561612 (C4 (Web Text))

Max Activating Token Index: 198

Text #14

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.0573. Min Act: -0.0000

Data Index: 1302307 (C4 (Web Text))

Max Activating Token Index: 928

Text #15

Max Range: 4.6776. Min Range: -4.6776

Max Act: 3.8825. Min Act: -0.0000

Data Index: 406487 (C4 (Web Text))

Max Activating Token Index: 769

Text #16

Max Range: 4.6776. Min Range: -4.6776

Max Act: 3.8301. Min Act: -0.0000

Data Index: 639813 (C4 (Web Text))

Max Activating Token Index: 841

Text #17

Max Range: 4.6776. Min Range: -4.6776

Max Act: 4.4878. Min Act: -0.0000

Data Index: 925961 (C4 (Web Text))

Max Activating Token Index: 683

Text #18

Max Range: 4.6776. Min Range: -4.6776

Max Act: 3.9865. Min Act: -0.0000

Data Index: 454813 (C4 (Web Text))

Max Activating Token Index: 490

Text #19

Max Range: 4.6776. Min Range: -4.6776

Max Act: 3.9565. Min Act: -0.0000

Data Index: 974787 (C4 (Web Text))

Max Activating Token Index: 437