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

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

Neuron 5054 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: 3.9742. Min Range: -3.9742

Max Act: 3.9742. Min Act: 0.0000

Data Index: 595308 (C4 (Web Text))

Max Activating Token Index: 221

Text #1

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.2395. Min Act: -0.0000

Data Index: 406375 (C4 (Web Text))

Max Activating Token Index: 691

Text #2

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.9461. Min Act: -0.0000

Data Index: 1411104 (Python Code)

Max Activating Token Index: 898

Text #3

Max Range: 3.9742. Min Range: -3.9742

Max Act: 3.0736. Min Act: -0.0000

Data Index: 1419706 (Python Code)

Max Activating Token Index: 549

Text #4

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.8494. Min Act: -0.0000

Data Index: 1077830 (C4 (Web Text))

Max Activating Token Index: 566

Text #5

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.9858. Min Act: -0.0000

Data Index: 1565542 (Python Code)

Max Activating Token Index: 299

Text #6

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.5863. Min Act: -0.0000

Data Index: 1405713 (Python Code)

Max Activating Token Index: 313

Text #7

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.7418. Min Act: -0.0000

Data Index: 1439433 (Python Code)

Max Activating Token Index: 568

Text #8

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.6666. Min Act: -0.0000

Data Index: 1576474 (Python Code)

Max Activating Token Index: 541

Text #9

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.4042. Min Act: -0.0000

Data Index: 1381656 (Python Code)

Max Activating Token Index: 428

Text #10

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.6267. Min Act: -0.0000

Data Index: 1581820 (Python Code)

Max Activating Token Index: 667

Text #11

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.6105. Min Act: -0.0000

Data Index: 1419747 (Python Code)

Max Activating Token Index: 832

Text #12

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.4658. Min Act: -0.0000

Data Index: 1630087 (Python Code)

Max Activating Token Index: 957

Text #13

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.6126. Min Act: 0.0001

Data Index: 1163328 (C4 (Web Text))

Max Activating Token Index: 531

Text #14

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.3127. Min Act: -0.0000

Data Index: 957889 (C4 (Web Text))

Max Activating Token Index: 157

Text #15

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.4114. Min Act: -0.0000

Data Index: 483292 (C4 (Web Text))

Max Activating Token Index: 801

Text #16

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.1224. Min Act: -0.0000

Data Index: 1382937 (Python Code)

Max Activating Token Index: 1016

Text #17

Max Range: 3.9742. Min Range: -3.9742

Max Act: 1.9907. Min Act: 0.0000

Data Index: 788309 (C4 (Web Text))

Max Activating Token Index: 248

Text #18

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.0462. Min Act: -0.0000

Data Index: 1526550 (Python Code)

Max Activating Token Index: 470

Text #19

Max Range: 3.9742. Min Range: -3.9742

Max Act: 2.0094. Min Act: 0.0001

Data Index: 828407 (C4 (Web Text))

Max Activating Token Index: 1004