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

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

Neuron 5062 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.6422. Min Act: -0.0000

Data Index: 420445 (C4 (Web Text))

Max Activating Token Index: 425

Text #1

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5800. Min Act: -0.0000

Data Index: 1269031 (C4 (Web Text))

Max Activating Token Index: 649

Text #2

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5757. Min Act: -0.0000

Data Index: 1067015 (C4 (Web Text))

Max Activating Token Index: 852

Text #3

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1197031 (C4 (Web Text))

Max Activating Token Index: 11

Text #4

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5846. Min Act: -0.0000

Data Index: 1234108 (C4 (Web Text))

Max Activating Token Index: 524

Text #5

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.6066. Min Act: -0.0000

Data Index: 1160289 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5643. Min Act: -0.0000

Data Index: 1118462 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5586. Min Act: -0.0000

Data Index: 912377 (C4 (Web Text))

Max Activating Token Index: 904

Text #8

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5251. Min Act: -0.0000

Data Index: 843134 (C4 (Web Text))

Max Activating Token Index: 151

Text #9

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5263. Min Act: -0.0000

Data Index: 835114 (C4 (Web Text))

Max Activating Token Index: 550

Text #10

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5244. Min Act: -0.0000

Data Index: 433888 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5401. Min Act: -0.0000

Data Index: 759925 (C4 (Web Text))

Max Activating Token Index: 851

Text #12

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5071. Min Act: -0.0000

Data Index: 162734 (C4 (Web Text))

Max Activating Token Index: 585

Text #13

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4965. Min Act: -0.0000

Data Index: 1159372 (C4 (Web Text))

Max Activating Token Index: 662

Text #14

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1321469 (C4 (Web Text))

Max Activating Token Index: 690

Text #15

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5139. Min Act: -0.0000

Data Index: 183008 (C4 (Web Text))

Max Activating Token Index: 367

Text #16

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5378. Min Act: -0.0000

Data Index: 30388 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5163. Min Act: -0.0000

Data Index: 1089999 (C4 (Web Text))

Max Activating Token Index: 767

Text #18

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.5004. Min Act: -0.0000

Data Index: 163366 (C4 (Web Text))

Max Activating Token Index: 337

Text #19

Max Range: 0.6422. Min Range: -0.6422

Max Act: 0.4827. Min Act: -0.0000

Data Index: 702378 (C4 (Web Text))

Max Activating Token Index: 1002