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

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

Neuron 3979 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: 1.8354. Min Range: -1.8354

Max Act: 1.8354. Min Act: -0.0000

Data Index: 1042205 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5713. Min Act: -0.0000

Data Index: 669446 (C4 (Web Text))

Max Activating Token Index: 78

Text #2

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6653. Min Act: -0.0000

Data Index: 369476 (C4 (Web Text))

Max Activating Token Index: 436

Text #3

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6235. Min Act: -0.0000

Data Index: 442690 (C4 (Web Text))

Max Activating Token Index: 284

Text #4

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6031. Min Act: -0.0000

Data Index: 354810 (C4 (Web Text))

Max Activating Token Index: 561

Text #5

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.6689. Min Act: -0.0000

Data Index: 1151061 (C4 (Web Text))

Max Activating Token Index: 231

Text #6

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.3049. Min Act: -0.0000

Data Index: 1049185 (C4 (Web Text))

Max Activating Token Index: 242

Text #7

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4086. Min Act: -0.0000

Data Index: 37597 (C4 (Web Text))

Max Activating Token Index: 379

Text #8

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.5389. Min Act: -0.0000

Data Index: 821042 (C4 (Web Text))

Max Activating Token Index: 275

Text #9

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4289. Min Act: -0.0000

Data Index: 155318 (C4 (Web Text))

Max Activating Token Index: 213

Text #10

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.3309. Min Act: -0.0000

Data Index: 86079 (C4 (Web Text))

Max Activating Token Index: 542

Text #11

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4828. Min Act: -0.0000

Data Index: 424242 (C4 (Web Text))

Max Activating Token Index: 241

Text #12

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.2534. Min Act: -0.0000

Data Index: 160745 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4333. Min Act: -0.0000

Data Index: 364278 (C4 (Web Text))

Max Activating Token Index: 373

Text #14

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.4415. Min Act: -0.0000

Data Index: 264390 (C4 (Web Text))

Max Activating Token Index: 608

Text #15

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.2477. Min Act: -0.0000

Data Index: 1015248 (C4 (Web Text))

Max Activating Token Index: 763

Text #16

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.2723. Min Act: -0.0000

Data Index: 480460 (C4 (Web Text))

Max Activating Token Index: 368

Text #17

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.3403. Min Act: -0.0000

Data Index: 1003856 (C4 (Web Text))

Max Activating Token Index: 988

Text #18

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.2277. Min Act: -0.0000

Data Index: 1135387 (C4 (Web Text))

Max Activating Token Index: 853

Text #19

Max Range: 1.8354. Min Range: -1.8354

Max Act: 1.2924. Min Act: -0.0000

Data Index: 1317397 (C4 (Web Text))

Max Activating Token Index: 184