Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 1638 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 6.9008. Min Range: -6.9008

Max Act: 6.9008. Min Act: -0.0000

Data Index: 742428 (C4 (Web Text))

Max Activating Token Index: 969

Text #1

Max Range: 6.9008. Min Range: -6.9008

Max Act: 6.6470. Min Act: -0.0000

Data Index: 64393 (C4 (Web Text))

Max Activating Token Index: 465

Text #2

Max Range: 6.9008. Min Range: -6.9008

Max Act: 6.5982. Min Act: -0.0000

Data Index: 230481 (C4 (Web Text))

Max Activating Token Index: 773

Text #3

Max Range: 6.9008. Min Range: -6.9008

Max Act: 6.2355. Min Act: -0.0000

Data Index: 878617 (C4 (Web Text))

Max Activating Token Index: 868

Text #4

Max Range: 6.9008. Min Range: -6.9008

Max Act: 6.0641. Min Act: -0.0000

Data Index: 1288280 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.9914. Min Act: -0.0000

Data Index: 1169776 (C4 (Web Text))

Max Activating Token Index: 1021

Text #6

Max Range: 6.9008. Min Range: -6.9008

Max Act: 6.0819. Min Act: -0.0000

Data Index: 295300 (C4 (Web Text))

Max Activating Token Index: 530

Text #7

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.7471. Min Act: -0.0000

Data Index: 378974 (C4 (Web Text))

Max Activating Token Index: 552

Text #8

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.6315. Min Act: -0.0000

Data Index: 678246 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.9001. Min Act: -0.0000

Data Index: 686939 (C4 (Web Text))

Max Activating Token Index: 664

Text #10

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.9466. Min Act: -0.0000

Data Index: 472262 (C4 (Web Text))

Max Activating Token Index: 974

Text #11

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.4677. Min Act: -0.0000

Data Index: 88763 (C4 (Web Text))

Max Activating Token Index: 798

Text #12

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.8814. Min Act: -0.0000

Data Index: 858421 (C4 (Web Text))

Max Activating Token Index: 952

Text #13

Max Range: 6.9008. Min Range: -6.9008

Max Act: 6.0582. Min Act: -0.0000

Data Index: 1342601 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.6552. Min Act: -0.0000

Data Index: 1350869 (C4 (Web Text))

Max Activating Token Index: 791

Text #15

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.9033. Min Act: -0.0000

Data Index: 492498 (C4 (Web Text))

Max Activating Token Index: 330

Text #16

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.6533. Min Act: -0.0000

Data Index: 608718 (C4 (Web Text))

Max Activating Token Index: 1005

Text #17

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.7460. Min Act: -0.0000

Data Index: 402689 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.9720. Min Act: -0.0000

Data Index: 534355 (C4 (Web Text))

Max Activating Token Index: 489

Text #19

Max Range: 6.9008. Min Range: -6.9008

Max Act: 5.9418. Min Act: -0.0000

Data Index: 531234 (C4 (Web Text))

Max Activating Token Index: 811