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

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

Neuron 1538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.2902. Min Range: -2.2902

Max Act: 2.2902. Min Act: -0.0000

Data Index: 1147384 (C4 (Web Text))

Max Activating Token Index: 729

Text #1

Max Range: 2.2902. Min Range: -2.2902

Max Act: 2.1453. Min Act: -0.0000

Data Index: 1328118 (C4 (Web Text))

Max Activating Token Index: 114

Text #2

Max Range: 2.2902. Min Range: -2.2902

Max Act: 2.2231. Min Act: -0.0000

Data Index: 962786 (C4 (Web Text))

Max Activating Token Index: 42

Text #3

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.8954. Min Act: -0.0000

Data Index: 24901 (C4 (Web Text))

Max Activating Token Index: 209

Text #4

Max Range: 2.2902. Min Range: -2.2902

Max Act: 2.0854. Min Act: -0.0000

Data Index: 755002 (C4 (Web Text))

Max Activating Token Index: 594

Text #5

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.9594. Min Act: -0.0000

Data Index: 438922 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.9159. Min Act: -0.0000

Data Index: 1151833 (C4 (Web Text))

Max Activating Token Index: 15

Text #7

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.8153. Min Act: -0.0000

Data Index: 464640 (C4 (Web Text))

Max Activating Token Index: 920

Text #8

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.6641. Min Act: -0.0000

Data Index: 539965 (C4 (Web Text))

Max Activating Token Index: 850

Text #9

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.6539. Min Act: -0.0000

Data Index: 998273 (C4 (Web Text))

Max Activating Token Index: 855

Text #10

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.7437. Min Act: -0.0000

Data Index: 1300921 (C4 (Web Text))

Max Activating Token Index: 352

Text #11

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.8138. Min Act: -0.0000

Data Index: 306533 (C4 (Web Text))

Max Activating Token Index: 350

Text #12

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.7194. Min Act: -0.0000

Data Index: 642820 (C4 (Web Text))

Max Activating Token Index: 881

Text #13

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.5452. Min Act: -0.0000

Data Index: 243536 (C4 (Web Text))

Max Activating Token Index: 836

Text #14

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.5505. Min Act: -0.0000

Data Index: 331705 (C4 (Web Text))

Max Activating Token Index: 828

Text #15

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.7150. Min Act: -0.0000

Data Index: 55401 (C4 (Web Text))

Max Activating Token Index: 1003

Text #16

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.5151. Min Act: -0.0000

Data Index: 423813 (C4 (Web Text))

Max Activating Token Index: 358

Text #17

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.5822. Min Act: -0.0000

Data Index: 249912 (C4 (Web Text))

Max Activating Token Index: 716

Text #18

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.6376. Min Act: -0.0000

Data Index: 1260411 (C4 (Web Text))

Max Activating Token Index: 358

Text #19

Max Range: 2.2902. Min Range: -2.2902

Max Act: 1.5445. Min Act: -0.0000

Data Index: 731732 (C4 (Web Text))

Max Activating Token Index: 579