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

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

Neuron 1405 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.9165. Min Act: -0.0000

Data Index: 401317 (C4 (Web Text))

Max Activating Token Index: 1004

Text #1

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.7789. Min Act: -0.0000

Data Index: 162664 (C4 (Web Text))

Max Activating Token Index: 384

Text #2

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.7274. Min Act: -0.0000

Data Index: 743100 (C4 (Web Text))

Max Activating Token Index: 874

Text #3

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6966. Min Act: -0.0000

Data Index: 715889 (C4 (Web Text))

Max Activating Token Index: 441

Text #4

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1309530 (C4 (Web Text))

Max Activating Token Index: 851

Text #5

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6677. Min Act: -0.0000

Data Index: 51870 (C4 (Web Text))

Max Activating Token Index: 622

Text #6

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6581. Min Act: -0.0000

Data Index: 961125 (C4 (Web Text))

Max Activating Token Index: 864

Text #7

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6597. Min Act: -0.0000

Data Index: 731793 (C4 (Web Text))

Max Activating Token Index: 707

Text #8

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6063. Min Act: -0.0000

Data Index: 1274139 (C4 (Web Text))

Max Activating Token Index: 949

Text #9

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6177. Min Act: -0.0000

Data Index: 322880 (C4 (Web Text))

Max Activating Token Index: 617

Text #10

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.5683. Min Act: -0.0000

Data Index: 975420 (C4 (Web Text))

Max Activating Token Index: 568

Text #11

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6215. Min Act: -0.0000

Data Index: 1453315 (Python Code)

Max Activating Token Index: 318

Text #12

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.5633. Min Act: -0.0000

Data Index: 918328 (C4 (Web Text))

Max Activating Token Index: 689

Text #13

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6012. Min Act: -0.0000

Data Index: 1218675 (C4 (Web Text))

Max Activating Token Index: 995

Text #14

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.5508. Min Act: -0.0000

Data Index: 445616 (C4 (Web Text))

Max Activating Token Index: 169

Text #15

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6256. Min Act: -0.0000

Data Index: 228110 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.5659. Min Act: -0.0000

Data Index: 227374 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.5743. Min Act: -0.0000

Data Index: 840897 (C4 (Web Text))

Max Activating Token Index: 749

Text #18

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.6089. Min Act: -0.0000

Data Index: 650789 (C4 (Web Text))

Max Activating Token Index: 535

Text #19

Max Range: 0.9165. Min Range: -0.9165

Max Act: 0.5779. Min Act: -0.0000

Data Index: 273472 (C4 (Web Text))

Max Activating Token Index: 272