Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4778 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.5387. Min Act: -0.0000

Data Index: 684551 (C4 (Web Text))

Max Activating Token Index: 236

Text #1

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4667. Min Act: -0.0000

Data Index: 302696 (C4 (Web Text))

Max Activating Token Index: 753

Text #2

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4474. Min Act: -0.0000

Data Index: 149750 (C4 (Web Text))

Max Activating Token Index: 135

Text #3

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4505. Min Act: -0.0000

Data Index: 1230761 (C4 (Web Text))

Max Activating Token Index: 942

Text #4

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4108. Min Act: -0.0000

Data Index: 1511993 (Python Code)

Max Activating Token Index: 557

Text #5

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4229. Min Act: -0.0000

Data Index: 317778 (C4 (Web Text))

Max Activating Token Index: 624

Text #6

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4162. Min Act: -0.0000

Data Index: 474089 (C4 (Web Text))

Max Activating Token Index: 990

Text #7

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.4380. Min Act: -0.0000

Data Index: 1390251 (Python Code)

Max Activating Token Index: 794

Text #8

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3893. Min Act: -0.0000

Data Index: 16043 (C4 (Web Text))

Max Activating Token Index: 408

Text #9

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3838. Min Act: -0.0000

Data Index: 1461993 (Python Code)

Max Activating Token Index: 417

Text #10

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3951. Min Act: -0.0000

Data Index: 903200 (C4 (Web Text))

Max Activating Token Index: 724

Text #11

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3887. Min Act: -0.0000

Data Index: 1269427 (C4 (Web Text))

Max Activating Token Index: 839

Text #12

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3774. Min Act: -0.0000

Data Index: 1317956 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3945. Min Act: -0.0000

Data Index: 790875 (C4 (Web Text))

Max Activating Token Index: 193

Text #14

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3539. Min Act: -0.0000

Data Index: 354769 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3611. Min Act: -0.0000

Data Index: 80994 (C4 (Web Text))

Max Activating Token Index: 939

Text #16

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3572. Min Act: -0.0000

Data Index: 1525617 (Python Code)

Max Activating Token Index: 295

Text #17

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3621. Min Act: -0.0000

Data Index: 1562811 (Python Code)

Max Activating Token Index: 437

Text #18

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3772. Min Act: -0.0000

Data Index: 521397 (C4 (Web Text))

Max Activating Token Index: 499

Text #19

Max Range: 0.5387. Min Range: -0.5387

Max Act: 0.3496. Min Act: -0.0000

Data Index: 1010341 (C4 (Web Text))

Max Activating Token Index: 262