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

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

Neuron 879 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: 0.9591. Min Range: -0.9591

Max Act: 0.9591. Min Act: -0.0000

Data Index: 492552 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.8042. Min Act: -0.0000

Data Index: 559596 (C4 (Web Text))

Max Activating Token Index: 107

Text #2

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.8047. Min Act: -0.0000

Data Index: 794277 (C4 (Web Text))

Max Activating Token Index: 725

Text #3

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6519. Min Act: -0.0000

Data Index: 414766 (C4 (Web Text))

Max Activating Token Index: 670

Text #4

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6728. Min Act: -0.0000

Data Index: 734797 (C4 (Web Text))

Max Activating Token Index: 776

Text #5

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.7132. Min Act: -0.0000

Data Index: 769141 (C4 (Web Text))

Max Activating Token Index: 342

Text #6

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6567. Min Act: -0.0000

Data Index: 417332 (C4 (Web Text))

Max Activating Token Index: 215

Text #7

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6686. Min Act: -0.0000

Data Index: 361110 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6729. Min Act: -0.0000

Data Index: 1010122 (C4 (Web Text))

Max Activating Token Index: 990

Text #9

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6364. Min Act: -0.0000

Data Index: 179947 (C4 (Web Text))

Max Activating Token Index: 804

Text #10

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6547. Min Act: -0.0000

Data Index: 1311768 (C4 (Web Text))

Max Activating Token Index: 290

Text #11

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6678. Min Act: -0.0000

Data Index: 1053574 (C4 (Web Text))

Max Activating Token Index: 213

Text #12

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6169. Min Act: -0.0000

Data Index: 208788 (C4 (Web Text))

Max Activating Token Index: 338

Text #13

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6366. Min Act: -0.0000

Data Index: 483150 (C4 (Web Text))

Max Activating Token Index: 285

Text #14

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6395. Min Act: -0.0000

Data Index: 1145998 (C4 (Web Text))

Max Activating Token Index: 951

Text #15

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6300. Min Act: -0.0000

Data Index: 345871 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6466. Min Act: -0.0000

Data Index: 466130 (C4 (Web Text))

Max Activating Token Index: 409

Text #17

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6071. Min Act: -0.0000

Data Index: 449564 (C4 (Web Text))

Max Activating Token Index: 660

Text #18

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.6031. Min Act: -0.0000

Data Index: 86812 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.9591. Min Range: -0.9591

Max Act: 0.5985. Min Act: -0.0000

Data Index: 1319721 (C4 (Web Text))

Max Activating Token Index: 579