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

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

Neuron 4993 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: 1.0387. Min Range: -1.0387

Max Act: 1.0081. Min Act: -0.0000

Data Index: 518847 (C4 (Web Text))

Max Activating Token Index: 1009

Text #1

Max Range: 1.0387. Min Range: -1.0387

Max Act: 1.0387. Min Act: -0.0000

Data Index: 908892 (C4 (Web Text))

Max Activating Token Index: 367

Text #2

Max Range: 1.0387. Min Range: -1.0387

Max Act: 1.0017. Min Act: -0.0000

Data Index: 921892 (C4 (Web Text))

Max Activating Token Index: 257

Text #3

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.9915. Min Act: -0.0000

Data Index: 207455 (C4 (Web Text))

Max Activating Token Index: 194

Text #4

Max Range: 1.0387. Min Range: -1.0387

Max Act: 1.0024. Min Act: -0.0000

Data Index: 430320 (C4 (Web Text))

Max Activating Token Index: 346

Text #5

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8872. Min Act: -0.0000

Data Index: 1148769 (C4 (Web Text))

Max Activating Token Index: 950

Text #6

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8546. Min Act: -0.0000

Data Index: 971605 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8357. Min Act: -0.0000

Data Index: 1302251 (C4 (Web Text))

Max Activating Token Index: 352

Text #8

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8966. Min Act: -0.0000

Data Index: 179220 (C4 (Web Text))

Max Activating Token Index: 330

Text #9

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8784. Min Act: -0.0000

Data Index: 469348 (C4 (Web Text))

Max Activating Token Index: 505

Text #10

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7679. Min Act: -0.0000

Data Index: 1040783 (C4 (Web Text))

Max Activating Token Index: 294

Text #11

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8730. Min Act: -0.0000

Data Index: 692977 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8109. Min Act: -0.0000

Data Index: 360430 (C4 (Web Text))

Max Activating Token Index: 556

Text #13

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8042. Min Act: -0.0000

Data Index: 611002 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8019. Min Act: -0.0000

Data Index: 847651 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8313. Min Act: -0.0000

Data Index: 886506 (C4 (Web Text))

Max Activating Token Index: 432

Text #16

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7886. Min Act: -0.0000

Data Index: 1044446 (C4 (Web Text))

Max Activating Token Index: 676

Text #17

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1221003 (C4 (Web Text))

Max Activating Token Index: 161

Text #18

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.8364. Min Act: -0.0000

Data Index: 904063 (C4 (Web Text))

Max Activating Token Index: 624

Text #19

Max Range: 1.0387. Min Range: -1.0387

Max Act: 0.7489. Min Act: -0.0000

Data Index: 730890 (C4 (Web Text))

Max Activating Token Index: 529