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

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

Neuron 1382 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.5059. Min Range: -2.5059

Max Act: 2.4187. Min Act: -0.0000

Data Index: 1566171 (Python Code)

Max Activating Token Index: 454

Text #1

Max Range: 2.5059. Min Range: -2.5059

Max Act: 2.5059. Min Act: -0.0000

Data Index: 333291 (C4 (Web Text))

Max Activating Token Index: 872

Text #2

Max Range: 2.5059. Min Range: -2.5059

Max Act: 2.3659. Min Act: -0.0000

Data Index: 818419 (C4 (Web Text))

Max Activating Token Index: 485

Text #3

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.9203. Min Act: -0.0000

Data Index: 1398370 (Python Code)

Max Activating Token Index: 546

Text #4

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.7829. Min Act: -0.0000

Data Index: 1532228 (Python Code)

Max Activating Token Index: 101

Text #5

Max Range: 2.5059. Min Range: -2.5059

Max Act: 2.2378. Min Act: -0.0000

Data Index: 1626981 (Python Code)

Max Activating Token Index: 330

Text #6

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.9157. Min Act: -0.0000

Data Index: 923404 (C4 (Web Text))

Max Activating Token Index: 724

Text #7

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.3657. Min Act: -0.0000

Data Index: 1325497 (C4 (Web Text))

Max Activating Token Index: 429

Text #8

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.3507. Min Act: -0.0000

Data Index: 973314 (C4 (Web Text))

Max Activating Token Index: 132

Text #9

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.2138. Min Act: -0.0000

Data Index: 1557153 (Python Code)

Max Activating Token Index: 645

Text #10

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1459148 (Python Code)

Max Activating Token Index: 927

Text #11

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.2131. Min Act: -0.0000

Data Index: 305576 (C4 (Web Text))

Max Activating Token Index: 273

Text #12

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.2982. Min Act: -0.0000

Data Index: 1337330 (C4 (Web Text))

Max Activating Token Index: 366

Text #13

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.5805. Min Act: -0.0000

Data Index: 546010 (C4 (Web Text))

Max Activating Token Index: 982

Text #14

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.1647. Min Act: -0.0000

Data Index: 1592561 (Python Code)

Max Activating Token Index: 170

Text #15

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.3696. Min Act: -0.0000

Data Index: 1509219 (Python Code)

Max Activating Token Index: 587

Text #16

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.3342. Min Act: -0.0000

Data Index: 1433278 (Python Code)

Max Activating Token Index: 656

Text #17

Max Range: 2.5059. Min Range: -2.5059

Max Act: 1.2532. Min Act: -0.0000

Data Index: 1508681 (Python Code)

Max Activating Token Index: 319

Text #18

Max Range: 2.5059. Min Range: -2.5059

Max Act: 0.9012. Min Act: -0.0000

Data Index: 1406963 (Python Code)

Max Activating Token Index: 247

Text #19

Max Range: 2.5059. Min Range: -2.5059

Max Act: 0.9403. Min Act: 0.0001

Data Index: 1244002 (C4 (Web Text))

Max Activating Token Index: 534