Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 15 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0601. Min Act: -0.0002

Data Index: 374035 (C4 (Web Text))

Max Activating Token Index: 228

Text #1

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0601. Min Act: -0.0002

Data Index: 837471 (C4 (Web Text))

Max Activating Token Index: 215

Text #2

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0608. Min Act: -0.0002

Data Index: 616055 (C4 (Web Text))

Max Activating Token Index: 495

Text #3

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0591. Min Act: -0.0002

Data Index: 52304 (C4 (Web Text))

Max Activating Token Index: 272

Text #4

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0593. Min Act: -0.0002

Data Index: 13530 (C4 (Web Text))

Max Activating Token Index: 584

Text #5

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0572. Min Act: -0.0002

Data Index: 902759 (C4 (Web Text))

Max Activating Token Index: 357

Text #6

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0562. Min Act: -0.0002

Data Index: 350584 (C4 (Web Text))

Max Activating Token Index: 262

Text #7

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0574. Min Act: -0.0002

Data Index: 1272549 (C4 (Web Text))

Max Activating Token Index: 808

Text #8

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1171620 (C4 (Web Text))

Max Activating Token Index: 1023

Text #9

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0540. Min Act: -0.0002

Data Index: 946424 (C4 (Web Text))

Max Activating Token Index: 358

Text #10

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0516. Min Act: -0.0002

Data Index: 851531 (C4 (Web Text))

Max Activating Token Index: 663

Text #11

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0535. Min Act: -0.0002

Data Index: 757608 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0561. Min Act: -0.0002

Data Index: 332840 (C4 (Web Text))

Max Activating Token Index: 296

Text #13

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0555. Min Act: -0.0002

Data Index: 377012 (C4 (Web Text))

Max Activating Token Index: 258

Text #14

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0571. Min Act: -0.0002

Data Index: 750838 (C4 (Web Text))

Max Activating Token Index: 141

Text #15

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0547. Min Act: -0.0002

Data Index: 1274434 (C4 (Web Text))

Max Activating Token Index: 438

Text #16

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0533. Min Act: -0.0002

Data Index: 866649 (C4 (Web Text))

Max Activating Token Index: 704

Text #17

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0537. Min Act: -0.0002

Data Index: 855263 (C4 (Web Text))

Max Activating Token Index: 695

Text #18

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0538. Min Act: -0.0002

Data Index: 183546 (C4 (Web Text))

Max Activating Token Index: 823

Text #19

Max Range: 0.0608. Min Range: -0.0608

Max Act: 0.0536. Min Act: -0.0002

Data Index: 868753 (C4 (Web Text))

Max Activating Token Index: 1023