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

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

Neuron 2355 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3688. Min Act: -0.0000

Data Index: 539313 (C4 (Web Text))

Max Activating Token Index: 384

Text #1

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.4101. Min Act: -0.0000

Data Index: 839415 (C4 (Web Text))

Max Activating Token Index: 697

Text #2

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3761. Min Act: -0.0000

Data Index: 610503 (C4 (Web Text))

Max Activating Token Index: 228

Text #3

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3601. Min Act: -0.0000

Data Index: 1216068 (C4 (Web Text))

Max Activating Token Index: 404

Text #4

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3555. Min Act: -0.0000

Data Index: 1055420 (C4 (Web Text))

Max Activating Token Index: 684

Text #5

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3321. Min Act: -0.0000

Data Index: 564577 (C4 (Web Text))

Max Activating Token Index: 657

Text #6

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3033. Min Act: -0.0000

Data Index: 852585 (C4 (Web Text))

Max Activating Token Index: 610

Text #7

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3044. Min Act: -0.0000

Data Index: 1580789 (Python Code)

Max Activating Token Index: 508

Text #8

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.3031. Min Act: -0.0000

Data Index: 310052 (C4 (Web Text))

Max Activating Token Index: 233

Text #9

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2867. Min Act: -0.0000

Data Index: 1017253 (C4 (Web Text))

Max Activating Token Index: 400

Text #10

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2754. Min Act: -0.0000

Data Index: 445487 (C4 (Web Text))

Max Activating Token Index: 603

Text #11

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2847. Min Act: -0.0000

Data Index: 237411 (C4 (Web Text))

Max Activating Token Index: 614

Text #12

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2833. Min Act: -0.0000

Data Index: 553188 (C4 (Web Text))

Max Activating Token Index: 882

Text #13

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2736. Min Act: -0.0000

Data Index: 1028091 (C4 (Web Text))

Max Activating Token Index: 902

Text #14

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2776. Min Act: -0.0000

Data Index: 871635 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2876. Min Act: -0.0000

Data Index: 410992 (C4 (Web Text))

Max Activating Token Index: 391

Text #16

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2676. Min Act: -0.0000

Data Index: 1346251 (C4 (Web Text))

Max Activating Token Index: 830

Text #17

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2815. Min Act: -0.0000

Data Index: 360640 (C4 (Web Text))

Max Activating Token Index: 734

Text #18

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2312. Min Act: -0.0000

Data Index: 776523 (C4 (Web Text))

Max Activating Token Index: 359

Text #19

Max Range: 0.4101. Min Range: -0.4101

Max Act: 0.2436. Min Act: -0.0000

Data Index: 377895 (C4 (Web Text))

Max Activating Token Index: 551