Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3982 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.8256. Min Act: -0.0001

Data Index: 817447 (C4 (Web Text))

Max Activating Token Index: 966

Text #1

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.1396. Min Act: -0.0001

Data Index: 35132 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.1540. Min Act: -0.0001

Data Index: 1105156 (C4 (Web Text))

Max Activating Token Index: 625

Text #3

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.0876. Min Act: -0.0001

Data Index: 388866 (C4 (Web Text))

Max Activating Token Index: 128

Text #4

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.0304. Min Act: -0.0001

Data Index: 234691 (C4 (Web Text))

Max Activating Token Index: 729

Text #5

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.0832. Min Act: -0.0001

Data Index: 790385 (C4 (Web Text))

Max Activating Token Index: 487

Text #6

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.0294. Min Act: -0.0001

Data Index: 1249714 (C4 (Web Text))

Max Activating Token Index: 615

Text #7

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9774. Min Act: -0.0001

Data Index: 960697 (C4 (Web Text))

Max Activating Token Index: 188

Text #8

Max Range: 1.8256. Min Range: -1.8256

Max Act: 1.0098. Min Act: -0.0001

Data Index: 733883 (C4 (Web Text))

Max Activating Token Index: 558

Text #9

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9808. Min Act: -0.0001

Data Index: 374183 (C4 (Web Text))

Max Activating Token Index: 443

Text #10

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9647. Min Act: -0.0001

Data Index: 676850 (C4 (Web Text))

Max Activating Token Index: 570

Text #11

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9730. Min Act: -0.0001

Data Index: 1184787 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9220. Min Act: -0.0001

Data Index: 880202 (C4 (Web Text))

Max Activating Token Index: 130

Text #13

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.8846. Min Act: -0.0001

Data Index: 523365 (C4 (Web Text))

Max Activating Token Index: 633

Text #14

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9364. Min Act: -0.0001

Data Index: 1041396 (C4 (Web Text))

Max Activating Token Index: 348

Text #15

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.8824. Min Act: -0.0001

Data Index: 475289 (C4 (Web Text))

Max Activating Token Index: 252

Text #16

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9350. Min Act: -0.0001

Data Index: 223035 (C4 (Web Text))

Max Activating Token Index: 632

Text #17

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9314. Min Act: -0.0001

Data Index: 1260938 (C4 (Web Text))

Max Activating Token Index: 575

Text #18

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.9049. Min Act: -0.0001

Data Index: 766771 (C4 (Web Text))

Max Activating Token Index: 971

Text #19

Max Range: 1.8256. Min Range: -1.8256

Max Act: 0.8684. Min Act: -0.0001

Data Index: 83414 (C4 (Web Text))

Max Activating Token Index: 730