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

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

Neuron 3910 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1420. Min Act: -0.0000

Data Index: 521150 (C4 (Web Text))

Max Activating Token Index: 680

Text #1

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1205. Min Act: -0.0000

Data Index: 1387009 (Python Code)

Max Activating Token Index: 780

Text #2

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1249. Min Act: -0.0000

Data Index: 1415630 (Python Code)

Max Activating Token Index: 807

Text #3

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1368. Min Act: -0.0000

Data Index: 1199466 (C4 (Web Text))

Max Activating Token Index: 667

Text #4

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1248. Min Act: -0.0000

Data Index: 1008466 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1224. Min Act: -0.0000

Data Index: 1294257 (C4 (Web Text))

Max Activating Token Index: 1007

Text #6

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1113. Min Act: -0.0000

Data Index: 1531070 (Python Code)

Max Activating Token Index: 543

Text #7

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1090. Min Act: -0.0000

Data Index: 1328789 (C4 (Web Text))

Max Activating Token Index: 105

Text #8

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1052. Min Act: -0.0000

Data Index: 70558 (C4 (Web Text))

Max Activating Token Index: 135

Text #9

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0983. Min Act: -0.0000

Data Index: 869484 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1006. Min Act: -0.0000

Data Index: 360135 (C4 (Web Text))

Max Activating Token Index: 723

Text #11

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1050. Min Act: -0.0000

Data Index: 1618329 (Python Code)

Max Activating Token Index: 963

Text #12

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1072. Min Act: -0.0000

Data Index: 773932 (C4 (Web Text))

Max Activating Token Index: 938

Text #13

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1068. Min Act: -0.0000

Data Index: 74240 (C4 (Web Text))

Max Activating Token Index: 544

Text #14

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0976. Min Act: -0.0000

Data Index: 712489 (C4 (Web Text))

Max Activating Token Index: 932

Text #15

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.1009. Min Act: -0.0000

Data Index: 1264422 (C4 (Web Text))

Max Activating Token Index: 585

Text #16

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0974. Min Act: -0.0000

Data Index: 703392 (C4 (Web Text))

Max Activating Token Index: 418

Text #17

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0984. Min Act: -0.0000

Data Index: 636960 (C4 (Web Text))

Max Activating Token Index: 282

Text #18

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0926. Min Act: -0.0000

Data Index: 856139 (C4 (Web Text))

Max Activating Token Index: 256

Text #19

Max Range: 0.1420. Min Range: -0.1420

Max Act: 0.0904. Min Act: -0.0000

Data Index: 891448 (C4 (Web Text))

Max Activating Token Index: 998