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

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

Neuron 3896 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: 1.2837. Min Range: -1.2837

Max Act: 1.2837. Min Act: -0.0000

Data Index: 306337 (C4 (Web Text))

Max Activating Token Index: 765

Text #1

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2702. Min Act: -0.0000

Data Index: 201156 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.2624. Min Act: -0.0000

Data Index: 1110873 (C4 (Web Text))

Max Activating Token Index: 129

Text #3

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.1119. Min Act: -0.0001

Data Index: 1172107 (C4 (Web Text))

Max Activating Token Index: 56

Text #4

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.1378. Min Act: -0.0000

Data Index: 1130653 (C4 (Web Text))

Max Activating Token Index: 428

Text #5

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.0654. Min Act: -0.0000

Data Index: 306034 (C4 (Web Text))

Max Activating Token Index: 355

Text #6

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.0832. Min Act: -0.0000

Data Index: 1174276 (C4 (Web Text))

Max Activating Token Index: 381

Text #7

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.0359. Min Act: -0.0000

Data Index: 217007 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8708. Min Act: -0.0000

Data Index: 655517 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 1.2837. Min Range: -1.2837

Max Act: 1.0086. Min Act: -0.0000

Data Index: 678976 (C4 (Web Text))

Max Activating Token Index: 38

Text #10

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9174. Min Act: -0.0000

Data Index: 679647 (C4 (Web Text))

Max Activating Token Index: 1005

Text #11

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9299. Min Act: -0.0000

Data Index: 942235 (C4 (Web Text))

Max Activating Token Index: 531

Text #12

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9974. Min Act: -0.0000

Data Index: 151652 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9921. Min Act: -0.0000

Data Index: 973480 (C4 (Web Text))

Max Activating Token Index: 882

Text #14

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8461. Min Act: -0.0000

Data Index: 1335990 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9063. Min Act: -0.0000

Data Index: 220057 (C4 (Web Text))

Max Activating Token Index: 520

Text #16

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9623. Min Act: -0.0000

Data Index: 664950 (C4 (Web Text))

Max Activating Token Index: 888

Text #17

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9203. Min Act: -0.0000

Data Index: 259539 (C4 (Web Text))

Max Activating Token Index: 195

Text #18

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.9235. Min Act: -0.0000

Data Index: 629551 (C4 (Web Text))

Max Activating Token Index: 453

Text #19

Max Range: 1.2837. Min Range: -1.2837

Max Act: 0.8532. Min Act: -0.0000

Data Index: 13116 (C4 (Web Text))

Max Activating Token Index: 75