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

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

Neuron 4759 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: 0.4387. Min Range: -0.4387

Max Act: 0.4387. Min Act: -0.0000

Data Index: 597714 (C4 (Web Text))

Max Activating Token Index: 972

Text #1

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3841. Min Act: -0.0000

Data Index: 502324 (C4 (Web Text))

Max Activating Token Index: 907

Text #2

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3775. Min Act: -0.0000

Data Index: 228756 (C4 (Web Text))

Max Activating Token Index: 138

Text #3

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3495. Min Act: -0.0000

Data Index: 880421 (C4 (Web Text))

Max Activating Token Index: 437

Text #4

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2951. Min Act: -0.0000

Data Index: 1293021 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2916. Min Act: -0.0000

Data Index: 657078 (C4 (Web Text))

Max Activating Token Index: 564

Text #6

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2942. Min Act: -0.0000

Data Index: 1013622 (C4 (Web Text))

Max Activating Token Index: 359

Text #7

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2808. Min Act: -0.0000

Data Index: 1112004 (C4 (Web Text))

Max Activating Token Index: 359

Text #8

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2700. Min Act: -0.0000

Data Index: 1001073 (C4 (Web Text))

Max Activating Token Index: 700

Text #9

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3281. Min Act: -0.0000

Data Index: 546506 (C4 (Web Text))

Max Activating Token Index: 919

Text #10

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2728. Min Act: -0.0000

Data Index: 1219484 (C4 (Web Text))

Max Activating Token Index: 749

Text #11

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2719. Min Act: -0.0000

Data Index: 1118714 (C4 (Web Text))

Max Activating Token Index: 293

Text #12

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2648. Min Act: -0.0000

Data Index: 737818 (C4 (Web Text))

Max Activating Token Index: 834

Text #13

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2633. Min Act: -0.0000

Data Index: 621342 (C4 (Web Text))

Max Activating Token Index: 299

Text #14

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2683. Min Act: -0.0000

Data Index: 1156874 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2442. Min Act: -0.0000

Data Index: 1231458 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2572. Min Act: -0.0000

Data Index: 947149 (C4 (Web Text))

Max Activating Token Index: 475

Text #17

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2551. Min Act: -0.0000

Data Index: 945187 (C4 (Web Text))

Max Activating Token Index: 400

Text #18

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2425. Min Act: -0.0000

Data Index: 508996 (C4 (Web Text))

Max Activating Token Index: 573

Text #19

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.2678. Min Act: -0.0000

Data Index: 655015 (C4 (Web Text))

Max Activating Token Index: 12