Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3655 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.4387. Min Act: -0.0000

Data Index: 57664 (C4 (Web Text))

Max Activating Token Index: 691

Text #1

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.4070. Min Act: -0.0000

Data Index: 990317 (C4 (Web Text))

Max Activating Token Index: 316

Text #2

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.4149. Min Act: 0.0000

Data Index: 985856 (C4 (Web Text))

Max Activating Token Index: 166

Text #3

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3814. Min Act: -0.0000

Data Index: 461453 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3880. Min Act: -0.0000

Data Index: 137958 (C4 (Web Text))

Max Activating Token Index: 148

Text #5

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3777. Min Act: -0.0000

Data Index: 969340 (C4 (Web Text))

Max Activating Token Index: 795

Text #6

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3719. Min Act: -0.0000

Data Index: 219896 (C4 (Web Text))

Max Activating Token Index: 790

Text #7

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3650. Min Act: -0.0000

Data Index: 1132222 (C4 (Web Text))

Max Activating Token Index: 981

Text #8

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3768. Min Act: -0.0001

Data Index: 63569 (C4 (Web Text))

Max Activating Token Index: 733

Text #9

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3569. Min Act: -0.0001

Data Index: 390881 (C4 (Web Text))

Max Activating Token Index: 813

Text #10

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3600. Min Act: -0.0000

Data Index: 556477 (C4 (Web Text))

Max Activating Token Index: 566

Text #11

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3550. Min Act: -0.0001

Data Index: 779901 (C4 (Web Text))

Max Activating Token Index: 716

Text #12

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3287. Min Act: -0.0000

Data Index: 1106117 (C4 (Web Text))

Max Activating Token Index: 602

Text #13

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3367. Min Act: -0.0000

Data Index: 6707 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3471. Min Act: -0.0000

Data Index: 232257 (C4 (Web Text))

Max Activating Token Index: 741

Text #15

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3347. Min Act: -0.0000

Data Index: 665359 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3219. Min Act: -0.0000

Data Index: 1219737 (C4 (Web Text))

Max Activating Token Index: 919

Text #17

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3303. Min Act: -0.0001

Data Index: 1068644 (C4 (Web Text))

Max Activating Token Index: 937

Text #18

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3217. Min Act: -0.0001

Data Index: 728207 (C4 (Web Text))

Max Activating Token Index: 584

Text #19

Max Range: 0.4387. Min Range: -0.4387

Max Act: 0.3279. Min Act: -0.0000

Data Index: 809947 (C4 (Web Text))

Max Activating Token Index: 70