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

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

Neuron 2726 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9709. Min Act: -0.0000

Data Index: 103819 (C4 (Web Text))

Max Activating Token Index: 282

Text #1

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8074. Min Act: -0.0000

Data Index: 677861 (C4 (Web Text))

Max Activating Token Index: 525

Text #2

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.9836. Min Act: -0.0000

Data Index: 172287 (C4 (Web Text))

Max Activating Token Index: 974

Text #3

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.7090. Min Act: -0.0000

Data Index: 1288620 (C4 (Web Text))

Max Activating Token Index: 940

Text #4

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8559. Min Act: -0.0000

Data Index: 1229828 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.8225. Min Act: -0.0000

Data Index: 313493 (C4 (Web Text))

Max Activating Token Index: 170

Text #6

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.6240. Min Act: -0.0000

Data Index: 125666 (C4 (Web Text))

Max Activating Token Index: 549

Text #7

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.7036. Min Act: -0.0000

Data Index: 228271 (C4 (Web Text))

Max Activating Token Index: 856

Text #8

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5651. Min Act: -0.0000

Data Index: 960339 (C4 (Web Text))

Max Activating Token Index: 58

Text #9

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5734. Min Act: -0.0000

Data Index: 115549 (C4 (Web Text))

Max Activating Token Index: 133

Text #10

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.7285. Min Act: -0.0000

Data Index: 413544 (C4 (Web Text))

Max Activating Token Index: 331

Text #11

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.4988. Min Act: -0.0000

Data Index: 282490 (C4 (Web Text))

Max Activating Token Index: 686

Text #12

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5883. Min Act: -0.0000

Data Index: 890784 (C4 (Web Text))

Max Activating Token Index: 404

Text #13

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5014. Min Act: -0.0000

Data Index: 684032 (C4 (Web Text))

Max Activating Token Index: 807

Text #14

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.6485. Min Act: -0.0000

Data Index: 1355372 (C4 (Web Text))

Max Activating Token Index: 787

Text #15

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5740. Min Act: -0.0000

Data Index: 257213 (C4 (Web Text))

Max Activating Token Index: 480

Text #16

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.7380. Min Act: -0.0000

Data Index: 1145585 (C4 (Web Text))

Max Activating Token Index: 786

Text #17

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.7335. Min Act: -0.0000

Data Index: 1015440 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5540. Min Act: -0.0000

Data Index: 864501 (C4 (Web Text))

Max Activating Token Index: 958

Text #19

Max Range: 1.9836. Min Range: -1.9836

Max Act: 1.5269. Min Act: -0.0000

Data Index: 1096341 (C4 (Web Text))

Max Activating Token Index: 186