Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 2287 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.4668. Min Act: -0.0000

Data Index: 842877 (C4 (Web Text))

Max Activating Token Index: 122

Text #1

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3921. Min Act: -0.0000

Data Index: 583452 (C4 (Web Text))

Max Activating Token Index: 95

Text #2

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3739. Min Act: -0.0000

Data Index: 1083473 (C4 (Web Text))

Max Activating Token Index: 377

Text #3

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3702. Min Act: -0.0000

Data Index: 938662 (C4 (Web Text))

Max Activating Token Index: 307

Text #4

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3424. Min Act: -0.0000

Data Index: 356121 (C4 (Web Text))

Max Activating Token Index: 25

Text #5

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3398. Min Act: -0.0000

Data Index: 74019 (C4 (Web Text))

Max Activating Token Index: 743

Text #6

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3394. Min Act: -0.0000

Data Index: 159637 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3474. Min Act: -0.0001

Data Index: 601626 (C4 (Web Text))

Max Activating Token Index: 226

Text #8

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3294. Min Act: -0.0000

Data Index: 493994 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3092. Min Act: -0.0000

Data Index: 1022818 (C4 (Web Text))

Max Activating Token Index: 608

Text #10

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3056. Min Act: -0.0000

Data Index: 1311943 (C4 (Web Text))

Max Activating Token Index: 436

Text #11

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.3053. Min Act: -0.0000

Data Index: 315670 (C4 (Web Text))

Max Activating Token Index: 476

Text #12

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2930. Min Act: -0.0001

Data Index: 284784 (C4 (Web Text))

Max Activating Token Index: 989

Text #13

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2789. Min Act: -0.0000

Data Index: 378130 (C4 (Web Text))

Max Activating Token Index: 455

Text #14

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2708. Min Act: -0.0000

Data Index: 345724 (C4 (Web Text))

Max Activating Token Index: 987

Text #15

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2759. Min Act: -0.0000

Data Index: 971691 (C4 (Web Text))

Max Activating Token Index: 449

Text #16

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2787. Min Act: -0.0000

Data Index: 649862 (C4 (Web Text))

Max Activating Token Index: 530

Text #17

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2668. Min Act: -0.0001

Data Index: 310399 (C4 (Web Text))

Max Activating Token Index: 67

Text #18

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2674. Min Act: -0.0001

Data Index: 670734 (C4 (Web Text))

Max Activating Token Index: 905

Text #19

Max Range: 0.4668. Min Range: -0.4668

Max Act: 0.2650. Min Act: -0.0000

Data Index: 691372 (C4 (Web Text))

Max Activating Token Index: 350