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

Dataset: The Pile

Neuron 3225 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.8353. Min Act: -0.0000

Data Index: 800975 (The Pile)

Max Activating Token Index: 44

Text #1

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7809. Min Act: -0.0000

Data Index: 253995 (The Pile)

Max Activating Token Index: 837

Text #2

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7521. Min Act: -0.0000

Data Index: 446959 (The Pile)

Max Activating Token Index: 454

Text #3

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7620. Min Act: -0.0000

Data Index: 1580673 (The Pile)

Max Activating Token Index: 718

Text #4

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7167. Min Act: -0.0000

Data Index: 878924 (The Pile)

Max Activating Token Index: 846

Text #5

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6622. Min Act: -0.0000

Data Index: 62361 (The Pile)

Max Activating Token Index: 139

Text #6

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.7928. Min Act: -0.0000

Data Index: 1526415 (The Pile)

Max Activating Token Index: 733

Text #7

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6712. Min Act: -0.0000

Data Index: 688333 (The Pile)

Max Activating Token Index: 579

Text #8

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.5414. Min Act: -0.0000

Data Index: 237412 (The Pile)

Max Activating Token Index: 814

Text #9

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6681. Min Act: -0.0000

Data Index: 1525222 (The Pile)

Max Activating Token Index: 359

Text #10

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6996. Min Act: -0.0000

Data Index: 884445 (The Pile)

Max Activating Token Index: 542

Text #11

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6386. Min Act: -0.0000

Data Index: 546711 (The Pile)

Max Activating Token Index: 726

Text #12

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6419. Min Act: -0.0000

Data Index: 1711546 (The Pile)

Max Activating Token Index: 673

Text #13

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6794. Min Act: -0.0000

Data Index: 1359690 (The Pile)

Max Activating Token Index: 559

Text #14

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.5823. Min Act: -0.0000

Data Index: 1073560 (The Pile)

Max Activating Token Index: 701

Text #15

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.5424. Min Act: -0.0000

Data Index: 263121 (The Pile)

Max Activating Token Index: 610

Text #16

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6287. Min Act: -0.0000

Data Index: 14505 (The Pile)

Max Activating Token Index: 51

Text #17

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6400. Min Act: -0.0000

Data Index: 851022 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.5817. Min Act: -0.0000

Data Index: 538718 (The Pile)

Max Activating Token Index: 164

Text #19

Max Range: 0.8353. Min Range: -0.8353

Max Act: 0.6050. Min Act: -0.0000

Data Index: 474520 (The Pile)

Max Activating Token Index: 950