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

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

Neuron 2091 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9192. Min Range: -3.9192

Max Act: 3.9192. Min Act: -0.0000

Data Index: 868604 (C4 (Web Text))

Max Activating Token Index: 676

Text #1

Max Range: 3.9192. Min Range: -3.9192

Max Act: 3.0904. Min Act: -0.0000

Data Index: 439416 (C4 (Web Text))

Max Activating Token Index: 960

Text #2

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.6859. Min Act: -0.0000

Data Index: 917013 (C4 (Web Text))

Max Activating Token Index: 618

Text #3

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.7338. Min Act: -0.0000

Data Index: 607819 (C4 (Web Text))

Max Activating Token Index: 346

Text #4

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.7536. Min Act: -0.0000

Data Index: 1041103 (C4 (Web Text))

Max Activating Token Index: 957

Text #5

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.7258. Min Act: -0.0000

Data Index: 1272653 (C4 (Web Text))

Max Activating Token Index: 751

Text #6

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.6615. Min Act: -0.0000

Data Index: 1606208 (Python Code)

Max Activating Token Index: 825

Text #7

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.2150. Min Act: -0.0000

Data Index: 1020065 (C4 (Web Text))

Max Activating Token Index: 846

Text #8

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.8596. Min Act: -0.0000

Data Index: 626666 (C4 (Web Text))

Max Activating Token Index: 822

Text #9

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.3829. Min Act: -0.0000

Data Index: 730 (C4 (Web Text))

Max Activating Token Index: 255

Text #10

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.3878. Min Act: -0.0000

Data Index: 997560 (C4 (Web Text))

Max Activating Token Index: 50

Text #11

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.3319. Min Act: -0.0000

Data Index: 1028116 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.6030. Min Act: -0.0000

Data Index: 969094 (C4 (Web Text))

Max Activating Token Index: 1008

Text #13

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.5869. Min Act: -0.0000

Data Index: 271066 (C4 (Web Text))

Max Activating Token Index: 44

Text #14

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.3084. Min Act: -0.0000

Data Index: 738836 (C4 (Web Text))

Max Activating Token Index: 93

Text #15

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.4239. Min Act: -0.0000

Data Index: 1637684 (Python Code)

Max Activating Token Index: 897

Text #16

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.2075. Min Act: -0.0000

Data Index: 1186364 (C4 (Web Text))

Max Activating Token Index: 755

Text #17

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.4251. Min Act: -0.0000

Data Index: 1442063 (Python Code)

Max Activating Token Index: 957

Text #18

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.2581. Min Act: -0.0000

Data Index: 1615922 (Python Code)

Max Activating Token Index: 293

Text #19

Max Range: 3.9192. Min Range: -3.9192

Max Act: 2.4066. Min Act: -0.0000

Data Index: 1460122 (Python Code)

Max Activating Token Index: 122