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

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

Neuron 4796 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.1101. Min Act: -0.0000

Data Index: 1380834 (Python Code)

Max Activating Token Index: 546

Text #1

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1098718 (C4 (Web Text))

Max Activating Token Index: 639

Text #2

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0802. Min Act: -0.0000

Data Index: 435622 (C4 (Web Text))

Max Activating Token Index: 650

Text #3

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0807. Min Act: -0.0000

Data Index: 1641802 (Python Code)

Max Activating Token Index: 594

Text #4

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0836. Min Act: -0.0000

Data Index: 1611316 (Python Code)

Max Activating Token Index: 941

Text #5

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0778. Min Act: -0.0000

Data Index: 765454 (C4 (Web Text))

Max Activating Token Index: 472

Text #6

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1556259 (Python Code)

Max Activating Token Index: 905

Text #7

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0709. Min Act: -0.0000

Data Index: 113926 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0664. Min Act: -0.0000

Data Index: 491546 (C4 (Web Text))

Max Activating Token Index: 352

Text #9

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0731. Min Act: -0.0000

Data Index: 132386 (C4 (Web Text))

Max Activating Token Index: 336

Text #10

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0707. Min Act: -0.0000

Data Index: 930775 (C4 (Web Text))

Max Activating Token Index: 493

Text #11

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0708. Min Act: -0.0000

Data Index: 1647451 (Python Code)

Max Activating Token Index: 474

Text #12

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0699. Min Act: -0.0000

Data Index: 849664 (C4 (Web Text))

Max Activating Token Index: 715

Text #13

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1116776 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0670. Min Act: -0.0000

Data Index: 1406633 (Python Code)

Max Activating Token Index: 323

Text #15

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0625. Min Act: -0.0000

Data Index: 38899 (C4 (Web Text))

Max Activating Token Index: 277

Text #16

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0648. Min Act: -0.0000

Data Index: 886578 (C4 (Web Text))

Max Activating Token Index: 457

Text #17

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0628. Min Act: -0.0000

Data Index: 1272365 (C4 (Web Text))

Max Activating Token Index: 565

Text #18

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0706. Min Act: -0.0000

Data Index: 331750 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.1101. Min Range: -0.1101

Max Act: 0.0674. Min Act: -0.0000

Data Index: 683732 (C4 (Web Text))

Max Activating Token Index: 731