Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 166 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.8445. Min Act: -0.0001

Data Index: 544166 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6914. Min Act: -0.0001

Data Index: 427390 (C4 (Web Text))

Max Activating Token Index: 437

Text #2

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6655. Min Act: -0.0000

Data Index: 962368 (C4 (Web Text))

Max Activating Token Index: 95

Text #3

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6039. Min Act: -0.0000

Data Index: 984394 (C4 (Web Text))

Max Activating Token Index: 897

Text #4

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.6409. Min Act: -0.0001

Data Index: 282156 (C4 (Web Text))

Max Activating Token Index: 645

Text #5

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5763. Min Act: -0.0001

Data Index: 698229 (C4 (Web Text))

Max Activating Token Index: 589

Text #6

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.4992. Min Act: -0.0001

Data Index: 350514 (C4 (Web Text))

Max Activating Token Index: 182

Text #7

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5602. Min Act: -0.0001

Data Index: 687890 (C4 (Web Text))

Max Activating Token Index: 862

Text #8

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5209. Min Act: -0.0001

Data Index: 1107125 (C4 (Web Text))

Max Activating Token Index: 143

Text #9

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5398. Min Act: -0.0001

Data Index: 1339559 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5142. Min Act: -0.0001

Data Index: 1085073 (C4 (Web Text))

Max Activating Token Index: 545

Text #11

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5021. Min Act: -0.0001

Data Index: 1326914 (C4 (Web Text))

Max Activating Token Index: 695

Text #12

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5065. Min Act: -0.0001

Data Index: 1332556 (C4 (Web Text))

Max Activating Token Index: 768

Text #13

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5185. Min Act: -0.0001

Data Index: 623670 (C4 (Web Text))

Max Activating Token Index: 989

Text #14

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5160. Min Act: -0.0001

Data Index: 531547 (C4 (Web Text))

Max Activating Token Index: 371

Text #15

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5259. Min Act: -0.0001

Data Index: 764812 (C4 (Web Text))

Max Activating Token Index: 675

Text #16

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.4424. Min Act: -0.0001

Data Index: 252691 (C4 (Web Text))

Max Activating Token Index: 562

Text #17

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.4455. Min Act: -0.0000

Data Index: 989389 (C4 (Web Text))

Max Activating Token Index: 888

Text #18

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.5234. Min Act: -0.0001

Data Index: 1064965 (C4 (Web Text))

Max Activating Token Index: 195

Text #19

Max Range: 0.8445. Min Range: -0.8445

Max Act: 0.4866. Min Act: -0.0001

Data Index: 742752 (C4 (Web Text))

Max Activating Token Index: 941