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

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

Neuron 3581 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: 1.0000. Min Range: -1.0000

Max Act: 1.0000. Min Act: -0.0000

Data Index: 933439 (C4 (Web Text))

Max Activating Token Index: 478

Text #1

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.9616. Min Act: -0.0000

Data Index: 1112278 (C4 (Web Text))

Max Activating Token Index: 762

Text #2

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.9400. Min Act: -0.0000

Data Index: 1019077 (C4 (Web Text))

Max Activating Token Index: 707

Text #3

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.9175. Min Act: -0.0000

Data Index: 172826 (C4 (Web Text))

Max Activating Token Index: 281

Text #4

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.9437. Min Act: -0.0000

Data Index: 268737 (C4 (Web Text))

Max Activating Token Index: 125

Text #5

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8970. Min Act: -0.0000

Data Index: 934563 (C4 (Web Text))

Max Activating Token Index: 37

Text #6

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8068. Min Act: -0.0000

Data Index: 119129 (C4 (Web Text))

Max Activating Token Index: 1019

Text #7

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8270. Min Act: -0.0000

Data Index: 727488 (C4 (Web Text))

Max Activating Token Index: 256

Text #8

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8645. Min Act: -0.0000

Data Index: 357250 (C4 (Web Text))

Max Activating Token Index: 249

Text #9

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7520. Min Act: -0.0000

Data Index: 65914 (C4 (Web Text))

Max Activating Token Index: 346

Text #10

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7613. Min Act: -0.0000

Data Index: 421085 (C4 (Web Text))

Max Activating Token Index: 254

Text #11

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7796. Min Act: -0.0000

Data Index: 1261568 (C4 (Web Text))

Max Activating Token Index: 432

Text #12

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8010. Min Act: -0.0000

Data Index: 910224 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7797. Min Act: -0.0000

Data Index: 1317990 (C4 (Web Text))

Max Activating Token Index: 159

Text #14

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7981. Min Act: -0.0000

Data Index: 1064174 (C4 (Web Text))

Max Activating Token Index: 285

Text #15

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.8044. Min Act: -0.0000

Data Index: 1169887 (C4 (Web Text))

Max Activating Token Index: 614

Text #16

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7447. Min Act: -0.0000

Data Index: 928302 (C4 (Web Text))

Max Activating Token Index: 654

Text #17

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7406. Min Act: -0.0000

Data Index: 62661 (C4 (Web Text))

Max Activating Token Index: 258

Text #18

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7552. Min Act: -0.0000

Data Index: 533348 (C4 (Web Text))

Max Activating Token Index: 954

Text #19

Max Range: 1.0000. Min Range: -1.0000

Max Act: 0.7491. Min Act: -0.0000

Data Index: 513874 (C4 (Web Text))

Max Activating Token Index: 382