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

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

Neuron 3609 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 15.6721. Min Range: -15.6721

Max Act: 15.6721. Min Act: -0.0000

Data Index: 502247 (C4 (Web Text))

Max Activating Token Index: 106

Text #1

Max Range: 15.6721. Min Range: -15.6721

Max Act: 5.9015. Min Act: -0.0000

Data Index: 114437 (C4 (Web Text))

Max Activating Token Index: 908

Text #2

Max Range: 15.6721. Min Range: -15.6721

Max Act: 6.8146. Min Act: -0.0000

Data Index: 1084174 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 15.6721. Min Range: -15.6721

Max Act: 3.4360. Min Act: -0.0000

Data Index: 1350900 (C4 (Web Text))

Max Activating Token Index: 397

Text #4

Max Range: 15.6721. Min Range: -15.6721

Max Act: 5.8627. Min Act: -0.0000

Data Index: 1315908 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.7036. Min Act: -0.0000

Data Index: 820909 (C4 (Web Text))

Max Activating Token Index: 364

Text #6

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.0510. Min Act: -0.0000

Data Index: 1031608 (C4 (Web Text))

Max Activating Token Index: 13

Text #7

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.1356. Min Act: -0.0000

Data Index: 1389269 (Python Code)

Max Activating Token Index: 153

Text #8

Max Range: 15.6721. Min Range: -15.6721

Max Act: 1.0018. Min Act: -0.0000

Data Index: 674202 (C4 (Web Text))

Max Activating Token Index: 190

Text #9

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.0601. Min Act: -0.0000

Data Index: 326604 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.1996. Min Act: -0.0000

Data Index: 18389 (C4 (Web Text))

Max Activating Token Index: 205

Text #11

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.0519. Min Act: -0.0000

Data Index: 1181086 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.1645. Min Act: -0.0000

Data Index: 79872 (C4 (Web Text))

Max Activating Token Index: 690

Text #13

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.1081. Min Act: -0.0000

Data Index: 39227 (C4 (Web Text))

Max Activating Token Index: 515

Text #14

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.1063. Min Act: -0.0000

Data Index: 235276 (C4 (Web Text))

Max Activating Token Index: 979

Text #15

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.0863. Min Act: -0.0000

Data Index: 1298192 (C4 (Web Text))

Max Activating Token Index: 325

Text #16

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.0738. Min Act: -0.0000

Data Index: 166745 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.0782. Min Act: -0.0000

Data Index: 1294360 (C4 (Web Text))

Max Activating Token Index: 1003

Text #18

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.0750. Min Act: 0.0000

Data Index: 387262 (C4 (Web Text))

Max Activating Token Index: 505

Text #19

Max Range: 15.6721. Min Range: -15.6721

Max Act: 0.0748. Min Act: -0.0000

Data Index: 28856 (C4 (Web Text))

Max Activating Token Index: 235