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

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

Neuron 3627 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4801. Min Range: -1.4801

Max Act: 1.1855. Min Act: -0.0001

Data Index: 150239 (C4 (Web Text))

Max Activating Token Index: 930

Text #1

Max Range: 1.4801. Min Range: -1.4801

Max Act: 1.4801. Min Act: -0.0001

Data Index: 829338 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9559. Min Act: -0.0001

Data Index: 1014505 (C4 (Web Text))

Max Activating Token Index: 685

Text #3

Max Range: 1.4801. Min Range: -1.4801

Max Act: 1.0865. Min Act: -0.0001

Data Index: 13724 (C4 (Web Text))

Max Activating Token Index: 293

Text #4

Max Range: 1.4801. Min Range: -1.4801

Max Act: 1.0324. Min Act: -0.0001

Data Index: 260692 (C4 (Web Text))

Max Activating Token Index: 981

Text #5

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9680. Min Act: -0.0001

Data Index: 417958 (C4 (Web Text))

Max Activating Token Index: 661

Text #6

Max Range: 1.4801. Min Range: -1.4801

Max Act: 1.0020. Min Act: -0.0001

Data Index: 445499 (C4 (Web Text))

Max Activating Token Index: 844

Text #7

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9323. Min Act: -0.0001

Data Index: 1052396 (C4 (Web Text))

Max Activating Token Index: 794

Text #8

Max Range: 1.4801. Min Range: -1.4801

Max Act: 1.0880. Min Act: -0.0001

Data Index: 464340 (C4 (Web Text))

Max Activating Token Index: 156

Text #9

Max Range: 1.4801. Min Range: -1.4801

Max Act: 1.0404. Min Act: -0.0001

Data Index: 854623 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.8595. Min Act: -0.0001

Data Index: 1159157 (C4 (Web Text))

Max Activating Token Index: 508

Text #11

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9315. Min Act: -0.0001

Data Index: 833972 (C4 (Web Text))

Max Activating Token Index: 199

Text #12

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9374. Min Act: -0.0001

Data Index: 320113 (C4 (Web Text))

Max Activating Token Index: 552

Text #13

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9325. Min Act: -0.0001

Data Index: 641220 (C4 (Web Text))

Max Activating Token Index: 705

Text #14

Max Range: 1.4801. Min Range: -1.4801

Max Act: 1.0130. Min Act: -0.0001

Data Index: 653231 (C4 (Web Text))

Max Activating Token Index: 887

Text #15

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.8810. Min Act: -0.0001

Data Index: 713339 (C4 (Web Text))

Max Activating Token Index: 658

Text #16

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9057. Min Act: -0.0001

Data Index: 49538 (C4 (Web Text))

Max Activating Token Index: 57

Text #17

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9584. Min Act: -0.0001

Data Index: 439133 (C4 (Web Text))

Max Activating Token Index: 564

Text #18

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.9122. Min Act: -0.0001

Data Index: 1264265 (C4 (Web Text))

Max Activating Token Index: 235

Text #19

Max Range: 1.4801. Min Range: -1.4801

Max Act: 0.8984. Min Act: -0.0001

Data Index: 1310050 (C4 (Web Text))

Max Activating Token Index: 26