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

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

Neuron 4959 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3527. Min Range: -1.3527

Max Act: 1.3527. Min Act: -0.0000

Data Index: 1532409 (Python Code)

Max Activating Token Index: 18

Text #1

Max Range: 1.3527. Min Range: -1.3527

Max Act: 1.0938. Min Act: -0.0000

Data Index: 1526043 (Python Code)

Max Activating Token Index: 528

Text #2

Max Range: 1.3527. Min Range: -1.3527

Max Act: 1.1506. Min Act: -0.0000

Data Index: 1548568 (Python Code)

Max Activating Token Index: 777

Text #3

Max Range: 1.3527. Min Range: -1.3527

Max Act: 1.1460. Min Act: -0.0000

Data Index: 470005 (C4 (Web Text))

Max Activating Token Index: 605

Text #4

Max Range: 1.3527. Min Range: -1.3527

Max Act: 1.0071. Min Act: 0.0000

Data Index: 1624381 (Python Code)

Max Activating Token Index: 121

Text #5

Max Range: 1.3527. Min Range: -1.3527

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1383611 (Python Code)

Max Activating Token Index: 1005

Text #6

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.9223. Min Act: -0.0000

Data Index: 1603976 (Python Code)

Max Activating Token Index: 534

Text #7

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.8848. Min Act: -0.0000

Data Index: 1428030 (Python Code)

Max Activating Token Index: 12

Text #8

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.8477. Min Act: -0.0000

Data Index: 1551791 (Python Code)

Max Activating Token Index: 93

Text #9

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.8079. Min Act: -0.0000

Data Index: 1419113 (Python Code)

Max Activating Token Index: 411

Text #10

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.8822. Min Act: -0.0000

Data Index: 1411943 (Python Code)

Max Activating Token Index: 695

Text #11

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.8043. Min Act: -0.0000

Data Index: 1521486 (Python Code)

Max Activating Token Index: 323

Text #12

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.7855. Min Act: -0.0000

Data Index: 1382167 (Python Code)

Max Activating Token Index: 116

Text #13

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.8343. Min Act: 0.0000

Data Index: 1504618 (Python Code)

Max Activating Token Index: 987

Text #14

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.7447. Min Act: 0.0000

Data Index: 1612300 (Python Code)

Max Activating Token Index: 18

Text #15

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.7032. Min Act: -0.0000

Data Index: 535822 (C4 (Web Text))

Max Activating Token Index: 754

Text #16

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.8080. Min Act: -0.0000

Data Index: 1433520 (Python Code)

Max Activating Token Index: 861

Text #17

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1105622 (C4 (Web Text))

Max Activating Token Index: 951

Text #18

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.6943. Min Act: -0.0000

Data Index: 1519333 (Python Code)

Max Activating Token Index: 856

Text #19

Max Range: 1.3527. Min Range: -1.3527

Max Act: 0.7246. Min Act: -0.0000

Data Index: 957416 (C4 (Web Text))

Max Activating Token Index: 487