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

Dataset: The Pile

Neuron 3562 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 9.3706. Min Range: -9.3706

Max Act: 9.1922. Min Act: -0.0000

Data Index: 1751276 (The Pile)

Max Activating Token Index: 162

Text #1

Max Range: 9.3706. Min Range: -9.3706

Max Act: 8.3077. Min Act: -0.0000

Data Index: 1731284 (The Pile)

Max Activating Token Index: 748

Text #2

Max Range: 9.3706. Min Range: -9.3706

Max Act: 9.3706. Min Act: -0.0000

Data Index: 1475693 (The Pile)

Max Activating Token Index: 87

Text #3

Max Range: 9.3706. Min Range: -9.3706

Max Act: 9.0624. Min Act: -0.0000

Data Index: 1304002 (The Pile)

Max Activating Token Index: 960

Text #4

Max Range: 9.3706. Min Range: -9.3706

Max Act: 8.4349. Min Act: -0.0000

Data Index: 1802387 (The Pile)

Max Activating Token Index: 309

Text #5

Max Range: 9.3706. Min Range: -9.3706

Max Act: 8.3320. Min Act: -0.0000

Data Index: 451115 (The Pile)

Max Activating Token Index: 249

Text #6

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.7688. Min Act: -0.0000

Data Index: 1269631 (The Pile)

Max Activating Token Index: 315

Text #7

Max Range: 9.3706. Min Range: -9.3706

Max Act: 8.3452. Min Act: -0.0000

Data Index: 1596407 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.6898. Min Act: -0.0000

Data Index: 1920936 (The Pile)

Max Activating Token Index: 400

Text #9

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.6871. Min Act: -0.0000

Data Index: 184289 (The Pile)

Max Activating Token Index: 398

Text #10

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.7009. Min Act: -0.0000

Data Index: 434147 (The Pile)

Max Activating Token Index: 941

Text #11

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.8195. Min Act: -0.0000

Data Index: 1914794 (The Pile)

Max Activating Token Index: 824

Text #12

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.0054. Min Act: -0.0000

Data Index: 1637483 (The Pile)

Max Activating Token Index: 1008

Text #13

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.7342. Min Act: -0.0000

Data Index: 758378 (The Pile)

Max Activating Token Index: 963

Text #14

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.7485. Min Act: -0.0000

Data Index: 63690 (The Pile)

Max Activating Token Index: 50

Text #15

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.3045. Min Act: -0.0000

Data Index: 340518 (The Pile)

Max Activating Token Index: 23

Text #16

Max Range: 9.3706. Min Range: -9.3706

Max Act: 7.0907. Min Act: -0.0000

Data Index: 847600 (The Pile)

Max Activating Token Index: 565

Text #17

Max Range: 9.3706. Min Range: -9.3706

Max Act: 6.7387. Min Act: -0.0000

Data Index: 1287131 (The Pile)

Max Activating Token Index: 547

Text #18

Max Range: 9.3706. Min Range: -9.3706

Max Act: 6.9757. Min Act: -0.0000

Data Index: 1249698 (The Pile)

Max Activating Token Index: 712

Text #19

Max Range: 9.3706. Min Range: -9.3706

Max Act: 5.4796. Min Act: -0.0000

Data Index: 3111 (The Pile)

Max Activating Token Index: 904