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

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

Neuron 975 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: 2.3013. Min Range: -2.3013

Max Act: 2.2161. Min Act: -0.0000

Data Index: 343082 (C4 (Web Text))

Max Activating Token Index: 138

Text #1

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.3013. Min Act: -0.0000

Data Index: 787788 (C4 (Web Text))

Max Activating Token Index: 341

Text #2

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.2588. Min Act: -0.0000

Data Index: 1170267 (C4 (Web Text))

Max Activating Token Index: 732

Text #3

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.0984. Min Act: -0.0000

Data Index: 1085252 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.1846. Min Act: -0.0000

Data Index: 152769 (C4 (Web Text))

Max Activating Token Index: 948

Text #5

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.1457. Min Act: -0.0000

Data Index: 1435672 (Python Code)

Max Activating Token Index: 915

Text #6

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.1449. Min Act: -0.0000

Data Index: 1289216 (C4 (Web Text))

Max Activating Token Index: 299

Text #7

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.1344. Min Act: -0.0000

Data Index: 1181983 (C4 (Web Text))

Max Activating Token Index: 1019

Text #8

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.2416. Min Act: -0.0000

Data Index: 214809 (C4 (Web Text))

Max Activating Token Index: 155

Text #9

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.1097. Min Act: -0.0000

Data Index: 587562 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.0757. Min Act: -0.0000

Data Index: 205789 (C4 (Web Text))

Max Activating Token Index: 79

Text #11

Max Range: 2.3013. Min Range: -2.3013

Max Act: 1.9433. Min Act: -0.0000

Data Index: 782412 (C4 (Web Text))

Max Activating Token Index: 292

Text #12

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.0066. Min Act: -0.0000

Data Index: 884645 (C4 (Web Text))

Max Activating Token Index: 729

Text #13

Max Range: 2.3013. Min Range: -2.3013

Max Act: 2.0365. Min Act: -0.0000

Data Index: 1457158 (Python Code)

Max Activating Token Index: 581

Text #14

Max Range: 2.3013. Min Range: -2.3013

Max Act: 1.9808. Min Act: -0.0000

Data Index: 319522 (C4 (Web Text))

Max Activating Token Index: 155

Text #15

Max Range: 2.3013. Min Range: -2.3013

Max Act: 1.9752. Min Act: -0.0000

Data Index: 559678 (C4 (Web Text))

Max Activating Token Index: 424

Text #16

Max Range: 2.3013. Min Range: -2.3013

Max Act: 1.9541. Min Act: -0.0000

Data Index: 798675 (C4 (Web Text))

Max Activating Token Index: 667

Text #17

Max Range: 2.3013. Min Range: -2.3013

Max Act: 1.9547. Min Act: -0.0000

Data Index: 30300 (C4 (Web Text))

Max Activating Token Index: 86

Text #18

Max Range: 2.3013. Min Range: -2.3013

Max Act: 1.9577. Min Act: -0.0000

Data Index: 325523 (C4 (Web Text))

Max Activating Token Index: 254

Text #19

Max Range: 2.3013. Min Range: -2.3013

Max Act: 1.9382. Min Act: -0.0000

Data Index: 1533769 (Python Code)

Max Activating Token Index: 494