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

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

Neuron 2357 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.6778. Min Act: -0.0000

Data Index: 904205 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.6031. Min Act: -0.0000

Data Index: 1025283 (C4 (Web Text))

Max Activating Token Index: 128

Text #2

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.4369. Min Act: -0.0000

Data Index: 1567454 (Python Code)

Max Activating Token Index: 832

Text #3

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.3498. Min Act: -0.0000

Data Index: 267788 (C4 (Web Text))

Max Activating Token Index: 775

Text #4

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.4823. Min Act: -0.0000

Data Index: 1283279 (C4 (Web Text))

Max Activating Token Index: 124

Text #5

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.1752. Min Act: -0.0000

Data Index: 83591 (C4 (Web Text))

Max Activating Token Index: 365

Text #6

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.0987. Min Act: -0.0000

Data Index: 571863 (C4 (Web Text))

Max Activating Token Index: 321

Text #7

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.1141. Min Act: -0.0000

Data Index: 479620 (C4 (Web Text))

Max Activating Token Index: 940

Text #8

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.9424. Min Act: -0.0000

Data Index: 815311 (C4 (Web Text))

Max Activating Token Index: 731

Text #9

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.0887. Min Act: -0.0000

Data Index: 1543107 (Python Code)

Max Activating Token Index: 1010

Text #10

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.9639. Min Act: -0.0000

Data Index: 1567838 (Python Code)

Max Activating Token Index: 789

Text #11

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.9752. Min Act: -0.0000

Data Index: 142982 (C4 (Web Text))

Max Activating Token Index: 384

Text #12

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.9823. Min Act: -0.0000

Data Index: 1056985 (C4 (Web Text))

Max Activating Token Index: 270

Text #13

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.9165. Min Act: -0.0000

Data Index: 1310559 (C4 (Web Text))

Max Activating Token Index: 51

Text #14

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.9175. Min Act: -0.0000

Data Index: 1397825 (Python Code)

Max Activating Token Index: 193

Text #15

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.8874. Min Act: -0.0000

Data Index: 91502 (C4 (Web Text))

Max Activating Token Index: 909

Text #16

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.7578. Min Act: -0.0000

Data Index: 282692 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1324237 (C4 (Web Text))

Max Activating Token Index: 52

Text #18

Max Range: 1.6778. Min Range: -1.6778

Max Act: 1.0236. Min Act: -0.0000

Data Index: 1086327 (C4 (Web Text))

Max Activating Token Index: 101

Text #19

Max Range: 1.6778. Min Range: -1.6778

Max Act: 0.8074. Min Act: -0.0000

Data Index: 734508 (C4 (Web Text))

Max Activating Token Index: 834