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

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

Neuron 5920 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0778. Min Range: -1.0778

Max Act: 1.0778. Min Act: -0.0000

Data Index: 1282184 (C4 (Web Text))

Max Activating Token Index: 346

Text #1

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.9922. Min Act: -0.0000

Data Index: 911318 (C4 (Web Text))

Max Activating Token Index: 912

Text #2

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.9590. Min Act: 0.0001

Data Index: 273855 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.9206. Min Act: -0.0000

Data Index: 1236190 (C4 (Web Text))

Max Activating Token Index: 809

Text #4

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8874. Min Act: -0.0000

Data Index: 238371 (C4 (Web Text))

Max Activating Token Index: 809

Text #5

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8730. Min Act: -0.0000

Data Index: 249581 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8708. Min Act: -0.0000

Data Index: 365360 (C4 (Web Text))

Max Activating Token Index: 11

Text #7

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8606. Min Act: -0.0000

Data Index: 8560 (C4 (Web Text))

Max Activating Token Index: 517

Text #8

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8625. Min Act: -0.0000

Data Index: 117996 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8536. Min Act: -0.0000

Data Index: 552261 (C4 (Web Text))

Max Activating Token Index: 351

Text #10

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.9101. Min Act: -0.0000

Data Index: 761784 (C4 (Web Text))

Max Activating Token Index: 326

Text #11

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8474. Min Act: 0.0000

Data Index: 567011 (C4 (Web Text))

Max Activating Token Index: 78

Text #12

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8446. Min Act: -0.0000

Data Index: 1071459 (C4 (Web Text))

Max Activating Token Index: 361

Text #13

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.7929. Min Act: 0.0000

Data Index: 81860 (C4 (Web Text))

Max Activating Token Index: 271

Text #14

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8368. Min Act: -0.0000

Data Index: 17722 (C4 (Web Text))

Max Activating Token Index: 106

Text #15

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8256. Min Act: -0.0000

Data Index: 274910 (C4 (Web Text))

Max Activating Token Index: 530

Text #16

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8232. Min Act: -0.0000

Data Index: 193490 (C4 (Web Text))

Max Activating Token Index: 337

Text #17

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8176. Min Act: -0.0000

Data Index: 477472 (C4 (Web Text))

Max Activating Token Index: 678

Text #18

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8138. Min Act: -0.0000

Data Index: 809339 (C4 (Web Text))

Max Activating Token Index: 591

Text #19

Max Range: 1.0778. Min Range: -1.0778

Max Act: 0.8110. Min Act: -0.0000

Data Index: 242878 (C4 (Web Text))

Max Activating Token Index: 311