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

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

Neuron 3254 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.6954. Min Act: -0.0000

Data Index: 6457 (C4 (Web Text))

Max Activating Token Index: 281

Text #1

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5963. Min Act: -0.0000

Data Index: 1018910 (C4 (Web Text))

Max Activating Token Index: 848

Text #2

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5939. Min Act: -0.0000

Data Index: 326604 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5662. Min Act: -0.0000

Data Index: 305474 (C4 (Web Text))

Max Activating Token Index: 846

Text #4

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5389. Min Act: -0.0000

Data Index: 1349600 (C4 (Web Text))

Max Activating Token Index: 179

Text #5

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5179. Min Act: -0.0000

Data Index: 1207478 (C4 (Web Text))

Max Activating Token Index: 1016

Text #6

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5392. Min Act: -0.0000

Data Index: 1293938 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5201. Min Act: -0.0000

Data Index: 599453 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5281. Min Act: -0.0000

Data Index: 782457 (C4 (Web Text))

Max Activating Token Index: 452

Text #9

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5215. Min Act: -0.0000

Data Index: 642902 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5229. Min Act: -0.0000

Data Index: 486681 (C4 (Web Text))

Max Activating Token Index: 182

Text #11

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4871. Min Act: -0.0000

Data Index: 277907 (C4 (Web Text))

Max Activating Token Index: 537

Text #12

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5029. Min Act: -0.0000

Data Index: 688557 (C4 (Web Text))

Max Activating Token Index: 756

Text #13

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5343. Min Act: -0.0000

Data Index: 460911 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.5181. Min Act: -0.0000

Data Index: 316111 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4853. Min Act: -0.0000

Data Index: 889796 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4977. Min Act: -0.0000

Data Index: 150534 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4966. Min Act: -0.0000

Data Index: 157194 (C4 (Web Text))

Max Activating Token Index: 1022

Text #18

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4749. Min Act: -0.0000

Data Index: 179155 (C4 (Web Text))

Max Activating Token Index: 542

Text #19

Max Range: 0.6954. Min Range: -0.6954

Max Act: 0.4872. Min Act: -0.0000

Data Index: 150499 (C4 (Web Text))

Max Activating Token Index: 725