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

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

Neuron 1785 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0192. Min Range: -1.0192

Max Act: 1.0192. Min Act: -0.0000

Data Index: 889232 (C4 (Web Text))

Max Activating Token Index: 654

Text #1

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.9131. Min Act: -0.0000

Data Index: 343458 (C4 (Web Text))

Max Activating Token Index: 898

Text #2

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8789. Min Act: -0.0000

Data Index: 1070331 (C4 (Web Text))

Max Activating Token Index: 251

Text #3

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.9452. Min Act: -0.0000

Data Index: 953662 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.9137. Min Act: -0.0000

Data Index: 18988 (C4 (Web Text))

Max Activating Token Index: 321

Text #5

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.9401. Min Act: -0.0000

Data Index: 341868 (C4 (Web Text))

Max Activating Token Index: 269

Text #6

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8493. Min Act: -0.0000

Data Index: 190973 (C4 (Web Text))

Max Activating Token Index: 869

Text #7

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8555. Min Act: -0.0000

Data Index: 1285839 (C4 (Web Text))

Max Activating Token Index: 436

Text #8

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8235. Min Act: -0.0000

Data Index: 1046927 (C4 (Web Text))

Max Activating Token Index: 610

Text #9

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8419. Min Act: -0.0000

Data Index: 320922 (C4 (Web Text))

Max Activating Token Index: 656

Text #10

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8177. Min Act: -0.0000

Data Index: 277022 (C4 (Web Text))

Max Activating Token Index: 353

Text #11

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.7836. Min Act: -0.0000

Data Index: 740038 (C4 (Web Text))

Max Activating Token Index: 417

Text #12

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8329. Min Act: -0.0000

Data Index: 675831 (C4 (Web Text))

Max Activating Token Index: 595

Text #13

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8573. Min Act: -0.0000

Data Index: 1228822 (C4 (Web Text))

Max Activating Token Index: 184

Text #14

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8048. Min Act: -0.0000

Data Index: 521134 (C4 (Web Text))

Max Activating Token Index: 70

Text #15

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8238. Min Act: -0.0000

Data Index: 686311 (C4 (Web Text))

Max Activating Token Index: 467

Text #16

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8383. Min Act: -0.0000

Data Index: 352864 (C4 (Web Text))

Max Activating Token Index: 401

Text #17

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8396. Min Act: -0.0000

Data Index: 577939 (C4 (Web Text))

Max Activating Token Index: 919

Text #18

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8310. Min Act: -0.0000

Data Index: 480791 (C4 (Web Text))

Max Activating Token Index: 692

Text #19

Max Range: 1.0192. Min Range: -1.0192

Max Act: 0.8021. Min Act: -0.0000

Data Index: 15415 (C4 (Web Text))

Max Activating Token Index: 428