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

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

Neuron 3182 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0769. Min Range: -1.0769

Max Act: 1.0769. Min Act: -0.0000

Data Index: 946156 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.9084. Min Act: -0.0000

Data Index: 63168 (C4 (Web Text))

Max Activating Token Index: 606

Text #2

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8608. Min Act: -0.0000

Data Index: 313848 (C4 (Web Text))

Max Activating Token Index: 747

Text #3

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.9051. Min Act: -0.0000

Data Index: 1180340 (C4 (Web Text))

Max Activating Token Index: 689

Text #4

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8536. Min Act: -0.0000

Data Index: 996498 (C4 (Web Text))

Max Activating Token Index: 318

Text #5

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8199. Min Act: -0.0000

Data Index: 1264388 (C4 (Web Text))

Max Activating Token Index: 1005

Text #6

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8406. Min Act: -0.0000

Data Index: 900124 (C4 (Web Text))

Max Activating Token Index: 386

Text #7

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8642. Min Act: -0.0000

Data Index: 398199 (C4 (Web Text))

Max Activating Token Index: 906

Text #8

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8578. Min Act: -0.0000

Data Index: 69885 (C4 (Web Text))

Max Activating Token Index: 647

Text #9

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8203. Min Act: -0.0000

Data Index: 486287 (C4 (Web Text))

Max Activating Token Index: 186

Text #10

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8197. Min Act: -0.0000

Data Index: 195882 (C4 (Web Text))

Max Activating Token Index: 367

Text #11

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7995. Min Act: -0.0000

Data Index: 564763 (C4 (Web Text))

Max Activating Token Index: 388

Text #12

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8121. Min Act: -0.0000

Data Index: 748813 (C4 (Web Text))

Max Activating Token Index: 122

Text #13

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8094. Min Act: -0.0000

Data Index: 335581 (C4 (Web Text))

Max Activating Token Index: 222

Text #14

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8349. Min Act: -0.0000

Data Index: 1161875 (C4 (Web Text))

Max Activating Token Index: 976

Text #15

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.8007. Min Act: -0.0000

Data Index: 980049 (C4 (Web Text))

Max Activating Token Index: 785

Text #16

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7949. Min Act: -0.0000

Data Index: 702752 (C4 (Web Text))

Max Activating Token Index: 1012

Text #17

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7952. Min Act: -0.0000

Data Index: 246361 (C4 (Web Text))

Max Activating Token Index: 132

Text #18

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7899. Min Act: -0.0000

Data Index: 705920 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 1.0769. Min Range: -1.0769

Max Act: 0.7617. Min Act: -0.0000

Data Index: 181821 (C4 (Web Text))

Max Activating Token Index: 49