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

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

Neuron 3582 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.7786. Min Act: -0.0000

Data Index: 1187186 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.7106. Min Act: -0.0000

Data Index: 32355 (C4 (Web Text))

Max Activating Token Index: 275

Text #2

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.6672. Min Act: -0.0000

Data Index: 94530 (C4 (Web Text))

Max Activating Token Index: 457

Text #3

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.5716. Min Act: -0.0000

Data Index: 298890 (C4 (Web Text))

Max Activating Token Index: 528

Text #4

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.5302. Min Act: -0.0000

Data Index: 971205 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.6079. Min Act: -0.0000

Data Index: 1037534 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.5952. Min Act: -0.0000

Data Index: 203764 (C4 (Web Text))

Max Activating Token Index: 283

Text #7

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.6344. Min Act: -0.0000

Data Index: 941319 (C4 (Web Text))

Max Activating Token Index: 270

Text #8

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.5081. Min Act: -0.0000

Data Index: 655616 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.5432. Min Act: -0.0000

Data Index: 1287071 (C4 (Web Text))

Max Activating Token Index: 157

Text #10

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.5344. Min Act: -0.0000

Data Index: 1003138 (C4 (Web Text))

Max Activating Token Index: 346

Text #11

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.4248. Min Act: -0.0000

Data Index: 553988 (C4 (Web Text))

Max Activating Token Index: 945

Text #12

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.4412. Min Act: -0.0000

Data Index: 642234 (C4 (Web Text))

Max Activating Token Index: 318

Text #13

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.4527. Min Act: -0.0000

Data Index: 253586 (C4 (Web Text))

Max Activating Token Index: 433

Text #14

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.4534. Min Act: -0.0000

Data Index: 175267 (C4 (Web Text))

Max Activating Token Index: 153

Text #15

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.4349. Min Act: -0.0000

Data Index: 197705 (C4 (Web Text))

Max Activating Token Index: 353

Text #16

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.4308. Min Act: -0.0000

Data Index: 610361 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.3253. Min Act: -0.0000

Data Index: 850765 (C4 (Web Text))

Max Activating Token Index: 708

Text #18

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.3652. Min Act: -0.0000

Data Index: 490676 (C4 (Web Text))

Max Activating Token Index: 273

Text #19

Max Range: 1.7786. Min Range: -1.7786

Max Act: 1.3447. Min Act: -0.0000

Data Index: 681306 (C4 (Web Text))

Max Activating Token Index: 71