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

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

Neuron 4400 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: 1.9387. Min Range: -1.9387

Max Act: 1.9387. Min Act: -0.0000

Data Index: 1584968 (Python Code)

Max Activating Token Index: 170

Text #1

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7803. Min Act: -0.0000

Data Index: 888539 (C4 (Web Text))

Max Activating Token Index: 923

Text #2

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.9039. Min Act: -0.0000

Data Index: 1632024 (Python Code)

Max Activating Token Index: 438

Text #3

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.8417. Min Act: -0.0000

Data Index: 1619622 (Python Code)

Max Activating Token Index: 454

Text #4

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.8278. Min Act: -0.0000

Data Index: 1032023 (C4 (Web Text))

Max Activating Token Index: 890

Text #5

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7663. Min Act: -0.0000

Data Index: 1264820 (C4 (Web Text))

Max Activating Token Index: 724

Text #6

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7726. Min Act: -0.0000

Data Index: 1147177 (C4 (Web Text))

Max Activating Token Index: 873

Text #7

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7263. Min Act: -0.0000

Data Index: 336255 (C4 (Web Text))

Max Activating Token Index: 864

Text #8

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.8792. Min Act: -0.0000

Data Index: 1625335 (Python Code)

Max Activating Token Index: 217

Text #9

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.6558. Min Act: -0.0000

Data Index: 237581 (C4 (Web Text))

Max Activating Token Index: 859

Text #10

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7533. Min Act: -0.0000

Data Index: 1360269 (Python Code)

Max Activating Token Index: 149

Text #11

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7054. Min Act: -0.0000

Data Index: 304767 (C4 (Web Text))

Max Activating Token Index: 392

Text #12

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.6887. Min Act: -0.0000

Data Index: 865855 (C4 (Web Text))

Max Activating Token Index: 838

Text #13

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.6859. Min Act: -0.0000

Data Index: 1155999 (C4 (Web Text))

Max Activating Token Index: 967

Text #14

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7348. Min Act: -0.0000

Data Index: 821818 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.7571. Min Act: -0.0000

Data Index: 440746 (C4 (Web Text))

Max Activating Token Index: 975

Text #16

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.6570. Min Act: -0.0000

Data Index: 118438 (C4 (Web Text))

Max Activating Token Index: 973

Text #17

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.6960. Min Act: -0.0000

Data Index: 1224811 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.6683. Min Act: -0.0000

Data Index: 950073 (C4 (Web Text))

Max Activating Token Index: 108

Text #19

Max Range: 1.9387. Min Range: -1.9387

Max Act: 1.6516. Min Act: -0.0000

Data Index: 178247 (C4 (Web Text))

Max Activating Token Index: 650