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

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

Neuron 3398 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.4083. Min Act: -0.0000

Data Index: 308520 (C4 (Web Text))

Max Activating Token Index: 610

Text #1

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.4067. Min Act: -0.0000

Data Index: 113670 (C4 (Web Text))

Max Activating Token Index: 319

Text #2

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3692. Min Act: -0.0000

Data Index: 403617 (C4 (Web Text))

Max Activating Token Index: 899

Text #3

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3696. Min Act: -0.0000

Data Index: 1046477 (C4 (Web Text))

Max Activating Token Index: 586

Text #4

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3688. Min Act: -0.0000

Data Index: 146939 (C4 (Web Text))

Max Activating Token Index: 172

Text #5

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3586. Min Act: -0.0000

Data Index: 523319 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3589. Min Act: -0.0000

Data Index: 1142877 (C4 (Web Text))

Max Activating Token Index: 305

Text #7

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3599. Min Act: -0.0000

Data Index: 767465 (C4 (Web Text))

Max Activating Token Index: 376

Text #8

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3579. Min Act: -0.0000

Data Index: 115616 (C4 (Web Text))

Max Activating Token Index: 363

Text #9

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3295. Min Act: -0.0000

Data Index: 774459 (C4 (Web Text))

Max Activating Token Index: 901

Text #10

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3503. Min Act: -0.0000

Data Index: 674111 (C4 (Web Text))

Max Activating Token Index: 679

Text #11

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3465. Min Act: -0.0000

Data Index: 495982 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3461. Min Act: -0.0000

Data Index: 1356841 (C4 (Web Text))

Max Activating Token Index: 995

Text #13

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3432. Min Act: -0.0000

Data Index: 431871 (C4 (Web Text))

Max Activating Token Index: 98

Text #14

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3417. Min Act: -0.0000

Data Index: 117737 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3408. Min Act: -0.0000

Data Index: 788968 (C4 (Web Text))

Max Activating Token Index: 383

Text #16

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3217. Min Act: -0.0000

Data Index: 1100598 (C4 (Web Text))

Max Activating Token Index: 909

Text #17

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3201. Min Act: -0.0000

Data Index: 397433 (C4 (Web Text))

Max Activating Token Index: 425

Text #18

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3184. Min Act: -0.0000

Data Index: 587355 (C4 (Web Text))

Max Activating Token Index: 768

Text #19

Max Range: 0.4083. Min Range: -0.4083

Max Act: 0.3374. Min Act: -0.0000

Data Index: 911086 (C4 (Web Text))

Max Activating Token Index: 407