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

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

Neuron 5040 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: 1.5387. Min Range: -1.5387

Max Act: 1.5387. Min Act: -0.0000

Data Index: 1053843 (C4 (Web Text))

Max Activating Token Index: 25

Text #1

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4533. Min Act: -0.0000

Data Index: 272689 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.3616. Min Act: -0.0000

Data Index: 918160 (C4 (Web Text))

Max Activating Token Index: 425

Text #3

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.3466. Min Act: -0.0000

Data Index: 1258472 (C4 (Web Text))

Max Activating Token Index: 747

Text #4

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.3715. Min Act: -0.0000

Data Index: 906459 (C4 (Web Text))

Max Activating Token Index: 668

Text #5

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.4562. Min Act: -0.0000

Data Index: 822357 (C4 (Web Text))

Max Activating Token Index: 840

Text #6

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2728. Min Act: -0.0000

Data Index: 661393 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2698. Min Act: -0.0000

Data Index: 145664 (C4 (Web Text))

Max Activating Token Index: 947

Text #8

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2047. Min Act: -0.0000

Data Index: 974308 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2101. Min Act: -0.0000

Data Index: 1135272 (C4 (Web Text))

Max Activating Token Index: 210

Text #10

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2760. Min Act: -0.0000

Data Index: 403688 (C4 (Web Text))

Max Activating Token Index: 801

Text #11

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2721. Min Act: -0.0000

Data Index: 459943 (C4 (Web Text))

Max Activating Token Index: 248

Text #12

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.3231. Min Act: -0.0000

Data Index: 991652 (C4 (Web Text))

Max Activating Token Index: 955

Text #13

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1945. Min Act: -0.0000

Data Index: 576860 (C4 (Web Text))

Max Activating Token Index: 176

Text #14

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1916. Min Act: -0.0000

Data Index: 1181517 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2494. Min Act: -0.0000

Data Index: 797539 (C4 (Web Text))

Max Activating Token Index: 387

Text #16

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2443. Min Act: -0.0000

Data Index: 712812 (C4 (Web Text))

Max Activating Token Index: 833

Text #17

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1419. Min Act: -0.0000

Data Index: 315984 (C4 (Web Text))

Max Activating Token Index: 739

Text #18

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.2414. Min Act: -0.0000

Data Index: 1164739 (C4 (Web Text))

Max Activating Token Index: 991

Text #19

Max Range: 1.5387. Min Range: -1.5387

Max Act: 1.1922. Min Act: -0.0000

Data Index: 503235 (C4 (Web Text))

Max Activating Token Index: 834