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

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

Neuron 4927 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: 0.3146. Min Range: -0.3146

Max Act: 0.3146. Min Act: -0.0000

Data Index: 1569816 (Python Code)

Max Activating Token Index: 586

Text #1

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.3054. Min Act: -0.0000

Data Index: 1594101 (Python Code)

Max Activating Token Index: 530

Text #2

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2591. Min Act: -0.0000

Data Index: 1413300 (Python Code)

Max Activating Token Index: 571

Text #3

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2864. Min Act: -0.0000

Data Index: 307201 (C4 (Web Text))

Max Activating Token Index: 788

Text #4

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2699. Min Act: -0.0000

Data Index: 1226122 (C4 (Web Text))

Max Activating Token Index: 184

Text #5

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2496. Min Act: -0.0000

Data Index: 1311104 (C4 (Web Text))

Max Activating Token Index: 406

Text #6

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2444. Min Act: -0.0000

Data Index: 548060 (C4 (Web Text))

Max Activating Token Index: 520

Text #7

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2438. Min Act: -0.0000

Data Index: 54627 (C4 (Web Text))

Max Activating Token Index: 96

Text #8

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2381. Min Act: -0.0000

Data Index: 1423767 (Python Code)

Max Activating Token Index: 468

Text #9

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2098. Min Act: -0.0000

Data Index: 27463 (C4 (Web Text))

Max Activating Token Index: 796

Text #10

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2288. Min Act: -0.0000

Data Index: 1638657 (Python Code)

Max Activating Token Index: 449

Text #11

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2353. Min Act: -0.0000

Data Index: 132711 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2320. Min Act: -0.0000

Data Index: 646159 (C4 (Web Text))

Max Activating Token Index: 547

Text #13

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2081. Min Act: -0.0000

Data Index: 1546168 (Python Code)

Max Activating Token Index: 635

Text #14

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2274. Min Act: -0.0000

Data Index: 1276541 (C4 (Web Text))

Max Activating Token Index: 870

Text #15

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2088. Min Act: -0.0000

Data Index: 1433894 (Python Code)

Max Activating Token Index: 315

Text #16

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2150. Min Act: -0.0000

Data Index: 1529541 (Python Code)

Max Activating Token Index: 828

Text #17

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2157. Min Act: -0.0000

Data Index: 32449 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2471. Min Act: -0.0000

Data Index: 1525044 (Python Code)

Max Activating Token Index: 656

Text #19

Max Range: 0.3146. Min Range: -0.3146

Max Act: 0.2200. Min Act: -0.0000

Data Index: 1094428 (C4 (Web Text))

Max Activating Token Index: 497