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

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

Neuron 4391 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6750. Min Act: -0.0001

Data Index: 163102 (C4 (Web Text))

Max Activating Token Index: 50

Text #1

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6538. Min Act: -0.0001

Data Index: 742091 (C4 (Web Text))

Max Activating Token Index: 270

Text #2

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6438. Min Act: -0.0001

Data Index: 1103836 (C4 (Web Text))

Max Activating Token Index: 46

Text #3

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6387. Min Act: -0.0001

Data Index: 474381 (C4 (Web Text))

Max Activating Token Index: 412

Text #4

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6426. Min Act: -0.0001

Data Index: 330034 (C4 (Web Text))

Max Activating Token Index: 929

Text #5

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6423. Min Act: -0.0001

Data Index: 638531 (C4 (Web Text))

Max Activating Token Index: 35

Text #6

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6397. Min Act: -0.0001

Data Index: 1080513 (C4 (Web Text))

Max Activating Token Index: 80

Text #7

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5842. Min Act: -0.0001

Data Index: 953579 (C4 (Web Text))

Max Activating Token Index: 921

Text #8

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5982. Min Act: -0.0001

Data Index: 599185 (C4 (Web Text))

Max Activating Token Index: 702

Text #9

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5998. Min Act: -0.0001

Data Index: 247800 (C4 (Web Text))

Max Activating Token Index: 111

Text #10

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6221. Min Act: -0.0001

Data Index: 1207857 (C4 (Web Text))

Max Activating Token Index: 248

Text #11

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6023. Min Act: -0.0001

Data Index: 78909 (C4 (Web Text))

Max Activating Token Index: 838

Text #12

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6105. Min Act: -0.0001

Data Index: 253758 (C4 (Web Text))

Max Activating Token Index: 770

Text #13

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5757. Min Act: -0.0001

Data Index: 107839 (C4 (Web Text))

Max Activating Token Index: 831

Text #14

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6147. Min Act: -0.0001

Data Index: 557002 (C4 (Web Text))

Max Activating Token Index: 293

Text #15

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5806. Min Act: -0.0001

Data Index: 471149 (C4 (Web Text))

Max Activating Token Index: 946

Text #16

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6123. Min Act: -0.0001

Data Index: 1276590 (C4 (Web Text))

Max Activating Token Index: 815

Text #17

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.5956. Min Act: -0.0001

Data Index: 255821 (C4 (Web Text))

Max Activating Token Index: 249

Text #18

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6104. Min Act: -0.0001

Data Index: 1084479 (C4 (Web Text))

Max Activating Token Index: 37

Text #19

Max Range: 0.6750. Min Range: -0.6750

Max Act: 0.6065. Min Act: -0.0001

Data Index: 287968 (C4 (Web Text))

Max Activating Token Index: 94