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

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

Neuron 1920 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 8.4387. Min Range: -8.4387

Max Act: 8.4387. Min Act: -0.0001

Data Index: 820726 (C4 (Web Text))

Max Activating Token Index: 233

Text #1

Max Range: 8.4387. Min Range: -8.4387

Max Act: 8.4342. Min Act: -0.0001

Data Index: 521383 (C4 (Web Text))

Max Activating Token Index: 568

Text #2

Max Range: 8.4387. Min Range: -8.4387

Max Act: 7.7726. Min Act: -0.0001

Data Index: 549218 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 8.4387. Min Range: -8.4387

Max Act: 7.2659. Min Act: -0.0001

Data Index: 315733 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 8.4387. Min Range: -8.4387

Max Act: 6.3705. Min Act: -0.0001

Data Index: 9207 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 8.4387. Min Range: -8.4387

Max Act: 6.0975. Min Act: -0.0001

Data Index: 337850 (C4 (Web Text))

Max Activating Token Index: 993

Text #6

Max Range: 8.4387. Min Range: -8.4387

Max Act: 6.0369. Min Act: -0.0001

Data Index: 1007861 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 8.4387. Min Range: -8.4387

Max Act: 5.9330. Min Act: -0.0001

Data Index: 1208402 (C4 (Web Text))

Max Activating Token Index: 652

Text #8

Max Range: 8.4387. Min Range: -8.4387

Max Act: 6.2567. Min Act: -0.0001

Data Index: 33230 (C4 (Web Text))

Max Activating Token Index: 269

Text #9

Max Range: 8.4387. Min Range: -8.4387

Max Act: 6.0082. Min Act: -0.0001

Data Index: 700993 (C4 (Web Text))

Max Activating Token Index: 365

Text #10

Max Range: 8.4387. Min Range: -8.4387

Max Act: 5.8796. Min Act: -0.0001

Data Index: 702735 (C4 (Web Text))

Max Activating Token Index: 108

Text #11

Max Range: 8.4387. Min Range: -8.4387

Max Act: 5.8404. Min Act: -0.0001

Data Index: 450116 (C4 (Web Text))

Max Activating Token Index: 131

Text #12

Max Range: 8.4387. Min Range: -8.4387

Max Act: 6.1225. Min Act: -0.0001

Data Index: 204639 (C4 (Web Text))

Max Activating Token Index: 302

Text #13

Max Range: 8.4387. Min Range: -8.4387

Max Act: 5.9750. Min Act: -0.0001

Data Index: 1150614 (C4 (Web Text))

Max Activating Token Index: 60

Text #14

Max Range: 8.4387. Min Range: -8.4387

Max Act: 5.9073. Min Act: -0.0001

Data Index: 738795 (C4 (Web Text))

Max Activating Token Index: 889

Text #15

Max Range: 8.4387. Min Range: -8.4387

Max Act: 5.8889. Min Act: -0.0001

Data Index: 981663 (C4 (Web Text))

Max Activating Token Index: 466

Text #16

Max Range: 8.4387. Min Range: -8.4387

Max Act: 6.2443. Min Act: -0.0001

Data Index: 1185320 (C4 (Web Text))

Max Activating Token Index: 175

Text #17

Max Range: 8.4387. Min Range: -8.4387

Max Act: 6.2344. Min Act: -0.0001

Data Index: 762378 (C4 (Web Text))

Max Activating Token Index: 32

Text #18

Max Range: 8.4387. Min Range: -8.4387

Max Act: 5.8211. Min Act: -0.0001

Data Index: 1212084 (C4 (Web Text))

Max Activating Token Index: 557

Text #19

Max Range: 8.4387. Min Range: -8.4387

Max Act: 5.9488. Min Act: -0.0001

Data Index: 441457 (C4 (Web Text))

Max Activating Token Index: 302