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

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

Neuron 4505 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.3170. Min Act: -0.0000

Data Index: 452946 (C4 (Web Text))

Max Activating Token Index: 161

Text #1

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9939. Min Act: -0.0000

Data Index: 565753 (C4 (Web Text))

Max Activating Token Index: 518

Text #2

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9966. Min Act: -0.0000

Data Index: 902964 (C4 (Web Text))

Max Activating Token Index: 828

Text #3

Max Range: 1.3170. Min Range: -1.3170

Max Act: 1.0289. Min Act: -0.0001

Data Index: 1056919 (C4 (Web Text))

Max Activating Token Index: 786

Text #4

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9382. Min Act: -0.0000

Data Index: 689361 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9182. Min Act: -0.0001

Data Index: 756112 (C4 (Web Text))

Max Activating Token Index: 649

Text #6

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.9123. Min Act: -0.0000

Data Index: 173678 (C4 (Web Text))

Max Activating Token Index: 621

Text #7

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8709. Min Act: -0.0000

Data Index: 198450 (C4 (Web Text))

Max Activating Token Index: 836

Text #8

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8819. Min Act: -0.0000

Data Index: 1093786 (C4 (Web Text))

Max Activating Token Index: 105

Text #9

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8660. Min Act: -0.0001

Data Index: 423122 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8548. Min Act: -0.0001

Data Index: 1205148 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8487. Min Act: -0.0001

Data Index: 116819 (C4 (Web Text))

Max Activating Token Index: 389

Text #12

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8362. Min Act: -0.0001

Data Index: 106306 (C4 (Web Text))

Max Activating Token Index: 444

Text #13

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8327. Min Act: -0.0000

Data Index: 387878 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8523. Min Act: -0.0000

Data Index: 1349724 (C4 (Web Text))

Max Activating Token Index: 258

Text #15

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1202284 (C4 (Web Text))

Max Activating Token Index: 771

Text #16

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1063180 (C4 (Web Text))

Max Activating Token Index: 905

Text #17

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.7940. Min Act: -0.0000

Data Index: 349105 (C4 (Web Text))

Max Activating Token Index: 464

Text #18

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8104. Min Act: -0.0001

Data Index: 299391 (C4 (Web Text))

Max Activating Token Index: 60

Text #19

Max Range: 1.3170. Min Range: -1.3170

Max Act: 0.8105. Min Act: -0.0001

Data Index: 419794 (C4 (Web Text))

Max Activating Token Index: 888