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

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

Neuron 5393 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5960. Min Act: 0.0000

Data Index: 901627 (C4 (Web Text))

Max Activating Token Index: 685

Text #1

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5686. Min Act: -0.0000

Data Index: 1128960 (C4 (Web Text))

Max Activating Token Index: 675

Text #2

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5238. Min Act: -0.0000

Data Index: 346496 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5284. Min Act: -0.0000

Data Index: 923095 (C4 (Web Text))

Max Activating Token Index: 820

Text #4

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5209. Min Act: -0.0000

Data Index: 106966 (C4 (Web Text))

Max Activating Token Index: 761

Text #5

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4956. Min Act: -0.0000

Data Index: 548676 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5128. Min Act: -0.0000

Data Index: 472192 (C4 (Web Text))

Max Activating Token Index: 333

Text #7

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4976. Min Act: -0.0000

Data Index: 835685 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.5010. Min Act: -0.0000

Data Index: 1214997 (C4 (Web Text))

Max Activating Token Index: 273

Text #9

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4864. Min Act: -0.0000

Data Index: 1181507 (C4 (Web Text))

Max Activating Token Index: 829

Text #10

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4987. Min Act: -0.0000

Data Index: 146153 (C4 (Web Text))

Max Activating Token Index: 197

Text #11

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4783. Min Act: -0.0000

Data Index: 748014 (C4 (Web Text))

Max Activating Token Index: 726

Text #12

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4660. Min Act: -0.0000

Data Index: 315083 (C4 (Web Text))

Max Activating Token Index: 769

Text #13

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4427. Min Act: -0.0000

Data Index: 125242 (C4 (Web Text))

Max Activating Token Index: 832

Text #14

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4998. Min Act: -0.0000

Data Index: 299161 (C4 (Web Text))

Max Activating Token Index: 909

Text #15

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4369. Min Act: -0.0000

Data Index: 741127 (C4 (Web Text))

Max Activating Token Index: 1017

Text #16

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4740. Min Act: -0.0000

Data Index: 364397 (C4 (Web Text))

Max Activating Token Index: 682

Text #17

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4623. Min Act: -0.0000

Data Index: 81771 (C4 (Web Text))

Max Activating Token Index: 572

Text #18

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4577. Min Act: -0.0000

Data Index: 612730 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.5960. Min Range: -0.5960

Max Act: 0.4713. Min Act: -0.0000

Data Index: 911058 (C4 (Web Text))

Max Activating Token Index: 73