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

Dataset: The Pile

Neuron 875 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4788. Min Act: -0.0000

Data Index: 1556 (The Pile)

Max Activating Token Index: 698

Text #1

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4102. Min Act: -0.0000

Data Index: 1048463 (The Pile)

Max Activating Token Index: 129

Text #2

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4077. Min Act: -0.0001

Data Index: 1011265 (The Pile)

Max Activating Token Index: 667

Text #3

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3925. Min Act: -0.0000

Data Index: 1496706 (The Pile)

Max Activating Token Index: 320

Text #4

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3734. Min Act: -0.0000

Data Index: 765481 (The Pile)

Max Activating Token Index: 35

Text #5

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3615. Min Act: -0.0000

Data Index: 1606844 (The Pile)

Max Activating Token Index: 383

Text #6

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.4006. Min Act: -0.0000

Data Index: 1596983 (The Pile)

Max Activating Token Index: 537

Text #7

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3725. Min Act: -0.0000

Data Index: 231045 (The Pile)

Max Activating Token Index: 41

Text #8

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3821. Min Act: -0.0000

Data Index: 1000358 (The Pile)

Max Activating Token Index: 851

Text #9

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3559. Min Act: -0.0000

Data Index: 54449 (The Pile)

Max Activating Token Index: 472

Text #10

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3685. Min Act: -0.0000

Data Index: 485860 (The Pile)

Max Activating Token Index: 278

Text #11

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3651. Min Act: -0.0000

Data Index: 1304295 (The Pile)

Max Activating Token Index: 267

Text #12

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3431. Min Act: -0.0000

Data Index: 128433 (The Pile)

Max Activating Token Index: 990

Text #13

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3456. Min Act: -0.0000

Data Index: 1637791 (The Pile)

Max Activating Token Index: 582

Text #14

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3177. Min Act: -0.0000

Data Index: 1359012 (The Pile)

Max Activating Token Index: 687

Text #15

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3413. Min Act: -0.0000

Data Index: 1738814 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3362. Min Act: -0.0000

Data Index: 510516 (The Pile)

Max Activating Token Index: 880

Text #17

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3705. Min Act: -0.0000

Data Index: 1917014 (The Pile)

Max Activating Token Index: 761

Text #18

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3224. Min Act: -0.0000

Data Index: 626739 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 0.4788. Min Range: -0.4788

Max Act: 0.3199. Min Act: -0.0000

Data Index: 39530 (The Pile)

Max Activating Token Index: 369