Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2680 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5632. Min Act: -0.0001

Data Index: 952686 (C4 (Web Text))

Max Activating Token Index: 526

Text #1

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5355. Min Act: -0.0001

Data Index: 1064363 (C4 (Web Text))

Max Activating Token Index: 961

Text #2

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5141. Min Act: -0.0001

Data Index: 422130 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5188. Min Act: -0.0001

Data Index: 1174324 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5040. Min Act: -0.0001

Data Index: 792223 (C4 (Web Text))

Max Activating Token Index: 952

Text #5

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5071. Min Act: -0.0001

Data Index: 521426 (C4 (Web Text))

Max Activating Token Index: 262

Text #6

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5164. Min Act: -0.0001

Data Index: 53904 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5132. Min Act: -0.0001

Data Index: 860888 (C4 (Web Text))

Max Activating Token Index: 1009

Text #8

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5022. Min Act: -0.0001

Data Index: 902743 (C4 (Web Text))

Max Activating Token Index: 855

Text #9

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4987. Min Act: -0.0001

Data Index: 488309 (C4 (Web Text))

Max Activating Token Index: 134

Text #10

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4796. Min Act: -0.0001

Data Index: 620904 (C4 (Web Text))

Max Activating Token Index: 460

Text #11

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4775. Min Act: -0.0001

Data Index: 126348 (C4 (Web Text))

Max Activating Token Index: 907

Text #12

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4935. Min Act: -0.0001

Data Index: 1126308 (C4 (Web Text))

Max Activating Token Index: 720

Text #13

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.5084. Min Act: -0.0001

Data Index: 799244 (C4 (Web Text))

Max Activating Token Index: 585

Text #14

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4904. Min Act: -0.0001

Data Index: 757459 (C4 (Web Text))

Max Activating Token Index: 558

Text #15

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4966. Min Act: -0.0001

Data Index: 801946 (C4 (Web Text))

Max Activating Token Index: 333

Text #16

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4781. Min Act: -0.0001

Data Index: 610131 (C4 (Web Text))

Max Activating Token Index: 1021

Text #17

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4618. Min Act: -0.0001

Data Index: 478114 (C4 (Web Text))

Max Activating Token Index: 557

Text #18

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4720. Min Act: -0.0001

Data Index: 301123 (C4 (Web Text))

Max Activating Token Index: 590

Text #19

Max Range: 0.5632. Min Range: -0.5632

Max Act: 0.4836. Min Act: -0.0001

Data Index: 373899 (C4 (Web Text))

Max Activating Token Index: 869