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

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

Neuron 3592 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5604. Min Act: -0.0000

Data Index: 125808 (C4 (Web Text))

Max Activating Token Index: 779

Text #1

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5642. Min Act: -0.0001

Data Index: 727917 (C4 (Web Text))

Max Activating Token Index: 900

Text #2

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5472. Min Act: -0.0001

Data Index: 816812 (C4 (Web Text))

Max Activating Token Index: 307

Text #3

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5420. Min Act: -0.0001

Data Index: 871161 (C4 (Web Text))

Max Activating Token Index: 904

Text #4

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5266. Min Act: -0.0000

Data Index: 340899 (C4 (Web Text))

Max Activating Token Index: 704

Text #5

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5548. Min Act: -0.0001

Data Index: 438743 (C4 (Web Text))

Max Activating Token Index: 952

Text #6

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5172. Min Act: -0.0001

Data Index: 597722 (C4 (Web Text))

Max Activating Token Index: 229

Text #7

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5444. Min Act: -0.0001

Data Index: 281812 (C4 (Web Text))

Max Activating Token Index: 961

Text #8

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5238. Min Act: -0.0001

Data Index: 399804 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5226. Min Act: -0.0001

Data Index: 221100 (C4 (Web Text))

Max Activating Token Index: 55

Text #10

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4994. Min Act: -0.0001

Data Index: 988457 (C4 (Web Text))

Max Activating Token Index: 383

Text #11

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5344. Min Act: -0.0001

Data Index: 303368 (C4 (Web Text))

Max Activating Token Index: 859

Text #12

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.4991. Min Act: -0.0001

Data Index: 958164 (C4 (Web Text))

Max Activating Token Index: 455

Text #13

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5132. Min Act: -0.0001

Data Index: 264180 (C4 (Web Text))

Max Activating Token Index: 259

Text #14

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5443. Min Act: -0.0001

Data Index: 1112071 (C4 (Web Text))

Max Activating Token Index: 355

Text #15

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5119. Min Act: -0.0001

Data Index: 1160864 (C4 (Web Text))

Max Activating Token Index: 7

Text #16

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5101. Min Act: -0.0001

Data Index: 1296428 (C4 (Web Text))

Max Activating Token Index: 298

Text #17

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5054. Min Act: -0.0001

Data Index: 239674 (C4 (Web Text))

Max Activating Token Index: 375

Text #18

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5084. Min Act: -0.0001

Data Index: 984627 (C4 (Web Text))

Max Activating Token Index: 25

Text #19

Max Range: 0.5642. Min Range: -0.5642

Max Act: 0.5201. Min Act: -0.0001

Data Index: 790077 (C4 (Web Text))

Max Activating Token Index: 18