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

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

Neuron 240 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: 2.2004. Min Range: -2.2004

Max Act: 2.2004. Min Act: -0.0000

Data Index: 1077196 (C4 (Web Text))

Max Activating Token Index: 509

Text #1

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.8834. Min Act: -0.0000

Data Index: 264024 (C4 (Web Text))

Max Activating Token Index: 460

Text #2

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.4515. Min Act: -0.0000

Data Index: 698021 (C4 (Web Text))

Max Activating Token Index: 12

Text #3

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.5876. Min Act: -0.0000

Data Index: 532285 (C4 (Web Text))

Max Activating Token Index: 648

Text #4

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.5555. Min Act: -0.0000

Data Index: 1325692 (C4 (Web Text))

Max Activating Token Index: 430

Text #5

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.5708. Min Act: -0.0000

Data Index: 1212614 (C4 (Web Text))

Max Activating Token Index: 187

Text #6

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.4780. Min Act: -0.0000

Data Index: 1212394 (C4 (Web Text))

Max Activating Token Index: 870

Text #7

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.6149. Min Act: -0.0000

Data Index: 311549 (C4 (Web Text))

Max Activating Token Index: 247

Text #8

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.6178. Min Act: -0.0000

Data Index: 986659 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.4924. Min Act: -0.0000

Data Index: 1202164 (C4 (Web Text))

Max Activating Token Index: 109

Text #10

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.3517. Min Act: -0.0000

Data Index: 1184640 (C4 (Web Text))

Max Activating Token Index: 14

Text #11

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.3892. Min Act: -0.0000

Data Index: 888647 (C4 (Web Text))

Max Activating Token Index: 554

Text #12

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.3002. Min Act: -0.0000

Data Index: 808726 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.2393. Min Act: -0.0000

Data Index: 279738 (C4 (Web Text))

Max Activating Token Index: 397

Text #14

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.3548. Min Act: -0.0000

Data Index: 524918 (C4 (Web Text))

Max Activating Token Index: 408

Text #15

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.3102. Min Act: -0.0000

Data Index: 495040 (C4 (Web Text))

Max Activating Token Index: 256

Text #16

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.2355. Min Act: -0.0000

Data Index: 608833 (C4 (Web Text))

Max Activating Token Index: 143

Text #17

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.2922. Min Act: -0.0000

Data Index: 864872 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.2278. Min Act: -0.0000

Data Index: 127801 (C4 (Web Text))

Max Activating Token Index: 754

Text #19

Max Range: 2.2004. Min Range: -2.2004

Max Act: 1.1379. Min Act: -0.0000

Data Index: 359375 (C4 (Web Text))

Max Activating Token Index: 379