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

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

Neuron 4888 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.6568. Min Act: -0.0000

Data Index: 100395 (C4 (Web Text))

Max Activating Token Index: 459

Text #1

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.6515. Min Act: -0.0000

Data Index: 838131 (C4 (Web Text))

Max Activating Token Index: 624

Text #2

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1302284 (C4 (Web Text))

Max Activating Token Index: 791

Text #3

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5134. Min Act: -0.0000

Data Index: 1599304 (Python Code)

Max Activating Token Index: 679

Text #4

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5546. Min Act: -0.0000

Data Index: 246034 (C4 (Web Text))

Max Activating Token Index: 649

Text #5

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5839. Min Act: -0.0000

Data Index: 849931 (C4 (Web Text))

Max Activating Token Index: 746

Text #6

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5725. Min Act: -0.0000

Data Index: 561940 (C4 (Web Text))

Max Activating Token Index: 750

Text #7

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5377. Min Act: -0.0000

Data Index: 821508 (C4 (Web Text))

Max Activating Token Index: 949

Text #8

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4976. Min Act: -0.0000

Data Index: 294658 (C4 (Web Text))

Max Activating Token Index: 526

Text #9

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5668. Min Act: -0.0000

Data Index: 770367 (C4 (Web Text))

Max Activating Token Index: 485

Text #10

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4660. Min Act: 0.0000

Data Index: 833974 (C4 (Web Text))

Max Activating Token Index: 607

Text #11

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4904. Min Act: -0.0000

Data Index: 204364 (C4 (Web Text))

Max Activating Token Index: 842

Text #12

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1135073 (C4 (Web Text))

Max Activating Token Index: 200

Text #13

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4601. Min Act: -0.0000

Data Index: 954496 (C4 (Web Text))

Max Activating Token Index: 47

Text #14

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4987. Min Act: -0.0000

Data Index: 1564449 (Python Code)

Max Activating Token Index: 156

Text #15

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4596. Min Act: 0.0000

Data Index: 631201 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4544. Min Act: -0.0000

Data Index: 57673 (C4 (Web Text))

Max Activating Token Index: 922

Text #17

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4151. Min Act: -0.0000

Data Index: 1216622 (C4 (Web Text))

Max Activating Token Index: 986

Text #18

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4446. Min Act: -0.0000

Data Index: 284682 (C4 (Web Text))

Max Activating Token Index: 737

Text #19

Max Range: 0.6568. Min Range: -0.6568

Max Act: 0.4330. Min Act: 0.0000

Data Index: 871582 (C4 (Web Text))

Max Activating Token Index: 417