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

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

Neuron 3546 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: 0.7748. Min Range: -0.7748

Max Act: 0.7660. Min Act: -0.0000

Data Index: 619564 (C4 (Web Text))

Max Activating Token Index: 743

Text #1

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.7748. Min Act: 0.0004

Data Index: 930599 (C4 (Web Text))

Max Activating Token Index: 523

Text #2

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.7213. Min Act: 0.0001

Data Index: 63959 (C4 (Web Text))

Max Activating Token Index: 273

Text #3

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6794. Min Act: -0.0000

Data Index: 117493 (C4 (Web Text))

Max Activating Token Index: 988

Text #4

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6574. Min Act: -0.0000

Data Index: 1063187 (C4 (Web Text))

Max Activating Token Index: 399

Text #5

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6377. Min Act: -0.0000

Data Index: 1319466 (C4 (Web Text))

Max Activating Token Index: 742

Text #6

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6305. Min Act: -0.0000

Data Index: 1208779 (C4 (Web Text))

Max Activating Token Index: 916

Text #7

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6409. Min Act: -0.0000

Data Index: 1179142 (C4 (Web Text))

Max Activating Token Index: 501

Text #8

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6160. Min Act: -0.0000

Data Index: 532684 (C4 (Web Text))

Max Activating Token Index: 329

Text #9

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6309. Min Act: 0.0000

Data Index: 846090 (C4 (Web Text))

Max Activating Token Index: 723

Text #10

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6137. Min Act: 0.0004

Data Index: 680269 (C4 (Web Text))

Max Activating Token Index: 26

Text #11

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5957. Min Act: -0.0000

Data Index: 1168202 (C4 (Web Text))

Max Activating Token Index: 602

Text #12

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.6060. Min Act: 0.0001

Data Index: 1281317 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5640. Min Act: -0.0000

Data Index: 1088818 (C4 (Web Text))

Max Activating Token Index: 477

Text #14

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5546. Min Act: 0.0001

Data Index: 1167338 (C4 (Web Text))

Max Activating Token Index: 333

Text #15

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5947. Min Act: 0.0000

Data Index: 609666 (C4 (Web Text))

Max Activating Token Index: 90

Text #16

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5360. Min Act: 0.0000

Data Index: 744301 (C4 (Web Text))

Max Activating Token Index: 304

Text #17

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5410. Min Act: -0.0000

Data Index: 1182779 (C4 (Web Text))

Max Activating Token Index: 191

Text #18

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5736. Min Act: 0.0002

Data Index: 687493 (C4 (Web Text))

Max Activating Token Index: 983

Text #19

Max Range: 0.7748. Min Range: -0.7748

Max Act: 0.5641. Min Act: -0.0000

Data Index: 889186 (C4 (Web Text))

Max Activating Token Index: 670