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

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

Neuron 3642 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.3067. Min Act: -0.0002

Data Index: 1195570 (C4 (Web Text))

Max Activating Token Index: 29

Text #1

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.1463. Min Act: -0.0002

Data Index: 535448 (C4 (Web Text))

Max Activating Token Index: 142

Text #2

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0070. Min Act: -0.0002

Data Index: 1279106 (C4 (Web Text))

Max Activating Token Index: 459

Text #3

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0287. Min Act: -0.0002

Data Index: 582285 (C4 (Web Text))

Max Activating Token Index: 47

Text #4

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9882. Min Act: -0.0002

Data Index: 1105785 (C4 (Web Text))

Max Activating Token Index: 44

Text #5

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0225. Min Act: -0.0002

Data Index: 345595 (C4 (Web Text))

Max Activating Token Index: 34

Text #6

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0040. Min Act: -0.0002

Data Index: 546289 (C4 (Web Text))

Max Activating Token Index: 33

Text #7

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9481. Min Act: -0.0002

Data Index: 680623 (C4 (Web Text))

Max Activating Token Index: 45

Text #8

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9686. Min Act: -0.0002

Data Index: 645080 (C4 (Web Text))

Max Activating Token Index: 146

Text #9

Max Range: 1.3067. Min Range: -1.3067

Max Act: 1.0123. Min Act: -0.0002

Data Index: 433958 (C4 (Web Text))

Max Activating Token Index: 347

Text #10

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9975. Min Act: -0.0002

Data Index: 371917 (C4 (Web Text))

Max Activating Token Index: 37

Text #11

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9504. Min Act: -0.0002

Data Index: 387048 (C4 (Web Text))

Max Activating Token Index: 35

Text #12

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9423. Min Act: -0.0002

Data Index: 1242605 (C4 (Web Text))

Max Activating Token Index: 44

Text #13

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9952. Min Act: -0.0002

Data Index: 873149 (C4 (Web Text))

Max Activating Token Index: 177

Text #14

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9581. Min Act: -0.0002

Data Index: 595583 (C4 (Web Text))

Max Activating Token Index: 34

Text #15

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9562. Min Act: -0.0002

Data Index: 164614 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9335. Min Act: -0.0002

Data Index: 672359 (C4 (Web Text))

Max Activating Token Index: 159

Text #17

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9204. Min Act: -0.0002

Data Index: 928164 (C4 (Web Text))

Max Activating Token Index: 28

Text #18

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9235. Min Act: -0.0002

Data Index: 959271 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 1.3067. Min Range: -1.3067

Max Act: 0.9214. Min Act: -0.0002

Data Index: 418712 (C4 (Web Text))

Max Activating Token Index: 30