Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3596 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.1450. Min Act: -0.0000

Data Index: 548408 (The Pile)

Max Activating Token Index: 685

Text #1

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.2753. Min Act: -0.0000

Data Index: 616029 (The Pile)

Max Activating Token Index: 350

Text #2

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.1603. Min Act: -0.0000

Data Index: 978963 (The Pile)

Max Activating Token Index: 689

Text #3

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.2574. Min Act: -0.0000

Data Index: 363079 (The Pile)

Max Activating Token Index: 570

Text #4

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.1108. Min Act: -0.0000

Data Index: 646765 (The Pile)

Max Activating Token Index: 55

Text #5

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1204803 (The Pile)

Max Activating Token Index: 845

Text #6

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0884. Min Act: -0.0000

Data Index: 1737856 (The Pile)

Max Activating Token Index: 465

Text #7

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0810. Min Act: -0.0000

Data Index: 1998000 (The Pile)

Max Activating Token Index: 393

Text #8

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0514. Min Act: -0.0000

Data Index: 1119654 (The Pile)

Max Activating Token Index: 302

Text #9

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0147. Min Act: -0.0000

Data Index: 854387 (The Pile)

Max Activating Token Index: 469

Text #10

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0289. Min Act: -0.0000

Data Index: 1783741 (The Pile)

Max Activating Token Index: 929

Text #11

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9975. Min Act: -0.0000

Data Index: 1057270 (The Pile)

Max Activating Token Index: 302

Text #12

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9853. Min Act: -0.0000

Data Index: 274081 (The Pile)

Max Activating Token Index: 140

Text #13

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8942. Min Act: -0.0000

Data Index: 654804 (The Pile)

Max Activating Token Index: 625

Text #14

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0732. Min Act: -0.0000

Data Index: 920457 (The Pile)

Max Activating Token Index: 594

Text #15

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.8875. Min Act: -0.0000

Data Index: 602302 (The Pile)

Max Activating Token Index: 440

Text #16

Max Range: 1.2753. Min Range: -1.2753

Max Act: 1.0017. Min Act: -0.0000

Data Index: 1348410 (The Pile)

Max Activating Token Index: 760

Text #17

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9653. Min Act: -0.0000

Data Index: 1707563 (The Pile)

Max Activating Token Index: 752

Text #18

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9165. Min Act: -0.0000

Data Index: 200895 (The Pile)

Max Activating Token Index: 191

Text #19

Max Range: 1.2753. Min Range: -1.2753

Max Act: 0.9961. Min Act: -0.0000

Data Index: 1008109 (The Pile)

Max Activating Token Index: 865