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

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

Neuron 2968 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.7948. Min Act: -0.0000

Data Index: 1596190 (Python Code)

Max Activating Token Index: 613

Text #1

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.3930. Min Act: -0.0000

Data Index: 1167624 (C4 (Web Text))

Max Activating Token Index: 406

Text #2

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.3406. Min Act: -0.0000

Data Index: 1290554 (C4 (Web Text))

Max Activating Token Index: 658

Text #3

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.3440. Min Act: -0.0000

Data Index: 1295611 (C4 (Web Text))

Max Activating Token Index: 226

Text #4

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1525. Min Act: -0.0000

Data Index: 1601896 (Python Code)

Max Activating Token Index: 733

Text #5

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.2110. Min Act: -0.0000

Data Index: 811372 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.2018. Min Act: -0.0000

Data Index: 555397 (C4 (Web Text))

Max Activating Token Index: 687

Text #7

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.2115. Min Act: -0.0000

Data Index: 301853 (C4 (Web Text))

Max Activating Token Index: 638

Text #8

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.2041. Min Act: -0.0000

Data Index: 70083 (C4 (Web Text))

Max Activating Token Index: 521

Text #9

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.2098. Min Act: -0.0000

Data Index: 371164 (C4 (Web Text))

Max Activating Token Index: 276

Text #10

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1878. Min Act: -0.0000

Data Index: 384018 (C4 (Web Text))

Max Activating Token Index: 153

Text #11

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.2286. Min Act: -0.0000

Data Index: 632828 (C4 (Web Text))

Max Activating Token Index: 401

Text #12

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.2149. Min Act: -0.0000

Data Index: 419439 (C4 (Web Text))

Max Activating Token Index: 548

Text #13

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1913. Min Act: -0.0000

Data Index: 944112 (C4 (Web Text))

Max Activating Token Index: 669

Text #14

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1826. Min Act: -0.0000

Data Index: 483678 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1795. Min Act: -0.0000

Data Index: 187257 (C4 (Web Text))

Max Activating Token Index: 686

Text #16

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1892. Min Act: -0.0000

Data Index: 997021 (C4 (Web Text))

Max Activating Token Index: 742

Text #17

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1796. Min Act: -0.0000

Data Index: 623660 (C4 (Web Text))

Max Activating Token Index: 92

Text #18

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1979. Min Act: -0.0000

Data Index: 922237 (C4 (Web Text))

Max Activating Token Index: 701

Text #19

Max Range: 1.7948. Min Range: -1.7948

Max Act: 1.1421. Min Act: -0.0000

Data Index: 813806 (C4 (Web Text))

Max Activating Token Index: 762