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

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

Neuron 4119 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.2130. Min Act: -0.0001

Data Index: 975165 (C4 (Web Text))

Max Activating Token Index: 648

Text #1

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.2075. Min Act: -0.0001

Data Index: 672091 (C4 (Web Text))

Max Activating Token Index: 679

Text #2

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1916. Min Act: -0.0001

Data Index: 1124023 (C4 (Web Text))

Max Activating Token Index: 308

Text #3

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1698. Min Act: -0.0001

Data Index: 324647 (C4 (Web Text))

Max Activating Token Index: 402

Text #4

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1816. Min Act: -0.0001

Data Index: 1059345 (C4 (Web Text))

Max Activating Token Index: 773

Text #5

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1441. Min Act: -0.0001

Data Index: 768213 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1584. Min Act: -0.0001

Data Index: 729705 (C4 (Web Text))

Max Activating Token Index: 989

Text #7

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1353. Min Act: -0.0001

Data Index: 860912 (C4 (Web Text))

Max Activating Token Index: 882

Text #8

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1664. Min Act: -0.0001

Data Index: 1160459 (C4 (Web Text))

Max Activating Token Index: 971

Text #9

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1564. Min Act: -0.0001

Data Index: 1310071 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1620. Min Act: -0.0001

Data Index: 41038 (C4 (Web Text))

Max Activating Token Index: 866

Text #11

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1534. Min Act: -0.0001

Data Index: 606395 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1412. Min Act: -0.0001

Data Index: 747490 (C4 (Web Text))

Max Activating Token Index: 752

Text #13

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1343. Min Act: -0.0001

Data Index: 1007965 (C4 (Web Text))

Max Activating Token Index: 388

Text #14

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1473. Min Act: -0.0001

Data Index: 1285563 (C4 (Web Text))

Max Activating Token Index: 430

Text #15

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1206. Min Act: -0.0001

Data Index: 721633 (C4 (Web Text))

Max Activating Token Index: 781

Text #16

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1469. Min Act: -0.0001

Data Index: 824224 (C4 (Web Text))

Max Activating Token Index: 545

Text #17

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1481. Min Act: -0.0001

Data Index: 148639 (C4 (Web Text))

Max Activating Token Index: 512

Text #18

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1688. Min Act: -0.0001

Data Index: 302765 (C4 (Web Text))

Max Activating Token Index: 956

Text #19

Max Range: 0.2130. Min Range: -0.2130

Max Act: 0.1432. Min Act: -0.0001

Data Index: 72879 (C4 (Web Text))

Max Activating Token Index: 439