Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1417 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.8521. Min Act: -0.0001

Data Index: 920645 (C4 (Web Text))

Max Activating Token Index: 901

Text #1

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7757. Min Act: -0.0001

Data Index: 532736 (C4 (Web Text))

Max Activating Token Index: 168

Text #2

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7132. Min Act: -0.0001

Data Index: 575769 (C4 (Web Text))

Max Activating Token Index: 980

Text #3

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.8813. Min Act: -0.0001

Data Index: 916986 (C4 (Web Text))

Max Activating Token Index: 483

Text #4

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6570. Min Act: -0.0001

Data Index: 788895 (C4 (Web Text))

Max Activating Token Index: 23

Text #5

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7156. Min Act: -0.0001

Data Index: 593600 (C4 (Web Text))

Max Activating Token Index: 49

Text #6

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.5552. Min Act: -0.0001

Data Index: 1102439 (C4 (Web Text))

Max Activating Token Index: 642

Text #7

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7252. Min Act: -0.0001

Data Index: 603104 (C4 (Web Text))

Max Activating Token Index: 388

Text #8

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6819. Min Act: -0.0001

Data Index: 1250520 (C4 (Web Text))

Max Activating Token Index: 849

Text #9

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.7036. Min Act: -0.0001

Data Index: 322680 (C4 (Web Text))

Max Activating Token Index: 340

Text #10

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6835. Min Act: -0.0001

Data Index: 236783 (C4 (Web Text))

Max Activating Token Index: 783

Text #11

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6611. Min Act: -0.0001

Data Index: 83255 (C4 (Web Text))

Max Activating Token Index: 856

Text #12

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6630. Min Act: -0.0001

Data Index: 625065 (C4 (Web Text))

Max Activating Token Index: 905

Text #13

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6194. Min Act: -0.0001

Data Index: 239207 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6507. Min Act: -0.0001

Data Index: 100482 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6945. Min Act: -0.0001

Data Index: 849863 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6655. Min Act: -0.0001

Data Index: 265564 (C4 (Web Text))

Max Activating Token Index: 357

Text #17

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6341. Min Act: -0.0001

Data Index: 1179521 (C4 (Web Text))

Max Activating Token Index: 305

Text #18

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6387. Min Act: -0.0001

Data Index: 466415 (C4 (Web Text))

Max Activating Token Index: 487

Text #19

Max Range: 0.8813. Min Range: -0.8813

Max Act: 0.6535. Min Act: -0.0001

Data Index: 7856 (C4 (Web Text))

Max Activating Token Index: 334