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

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

Neuron 4282 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0624. Min Act: -0.0002

Data Index: 1095950 (C4 (Web Text))

Max Activating Token Index: 322

Text #1

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1194229 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0541. Min Act: -0.0002

Data Index: 1182507 (C4 (Web Text))

Max Activating Token Index: 260

Text #3

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0534. Min Act: -0.0002

Data Index: 515837 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0536. Min Act: -0.0002

Data Index: 6615 (C4 (Web Text))

Max Activating Token Index: 37

Text #5

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0553. Min Act: -0.0002

Data Index: 41416 (C4 (Web Text))

Max Activating Token Index: 224

Text #6

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0526. Min Act: -0.0002

Data Index: 418056 (C4 (Web Text))

Max Activating Token Index: 518

Text #7

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0531. Min Act: -0.0002

Data Index: 248103 (C4 (Web Text))

Max Activating Token Index: 518

Text #8

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0558. Min Act: -0.0002

Data Index: 406810 (C4 (Web Text))

Max Activating Token Index: 830

Text #9

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0548. Min Act: -0.0002

Data Index: 140644 (C4 (Web Text))

Max Activating Token Index: 799

Text #10

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1126522 (C4 (Web Text))

Max Activating Token Index: 299

Text #11

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0522. Min Act: -0.0002

Data Index: 950197 (C4 (Web Text))

Max Activating Token Index: 36

Text #12

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0496. Min Act: -0.0002

Data Index: 445153 (C4 (Web Text))

Max Activating Token Index: 63

Text #13

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0503. Min Act: -0.0002

Data Index: 1299275 (C4 (Web Text))

Max Activating Token Index: 811

Text #14

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0457. Min Act: -0.0002

Data Index: 734557 (C4 (Web Text))

Max Activating Token Index: 864

Text #15

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0492. Min Act: -0.0002

Data Index: 686770 (C4 (Web Text))

Max Activating Token Index: 779

Text #16

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0456. Min Act: -0.0002

Data Index: 602572 (C4 (Web Text))

Max Activating Token Index: 653

Text #17

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0465. Min Act: -0.0002

Data Index: 223039 (C4 (Web Text))

Max Activating Token Index: 60

Text #18

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0483. Min Act: -0.0002

Data Index: 281142 (C4 (Web Text))

Max Activating Token Index: 965

Text #19

Max Range: 0.0624. Min Range: -0.0624

Max Act: 0.0441. Min Act: -0.0002

Data Index: 1054817 (C4 (Web Text))

Max Activating Token Index: 927