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

Dataset: The Pile

Neuron 4298 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: 1.7594. Min Range: -1.7594

Max Act: 1.7594. Min Act: -0.0000

Data Index: 1665898 (The Pile)

Max Activating Token Index: 424

Text #1

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5652. Min Act: -0.0000

Data Index: 657343 (The Pile)

Max Activating Token Index: 281

Text #2

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5498. Min Act: -0.0000

Data Index: 1685948 (The Pile)

Max Activating Token Index: 471

Text #3

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4125. Min Act: -0.0000

Data Index: 1923562 (The Pile)

Max Activating Token Index: 178

Text #4

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3844. Min Act: -0.0000

Data Index: 338003 (The Pile)

Max Activating Token Index: 108

Text #5

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.5488. Min Act: -0.0000

Data Index: 552398 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4469. Min Act: -0.0000

Data Index: 1082043 (The Pile)

Max Activating Token Index: 354

Text #7

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3623. Min Act: 0.0000

Data Index: 1416829 (The Pile)

Max Activating Token Index: 933

Text #8

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4373. Min Act: 0.0000

Data Index: 1651763 (The Pile)

Max Activating Token Index: 27

Text #9

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4076. Min Act: -0.0000

Data Index: 492238 (The Pile)

Max Activating Token Index: 888

Text #10

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3341. Min Act: -0.0000

Data Index: 772115 (The Pile)

Max Activating Token Index: 229

Text #11

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3340. Min Act: -0.0000

Data Index: 312424 (The Pile)

Max Activating Token Index: 641

Text #12

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3927. Min Act: -0.0000

Data Index: 1940665 (The Pile)

Max Activating Token Index: 112

Text #13

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3717. Min Act: -0.0000

Data Index: 1163973 (The Pile)

Max Activating Token Index: 224

Text #14

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.4357. Min Act: -0.0000

Data Index: 692768 (The Pile)

Max Activating Token Index: 146

Text #15

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3418. Min Act: -0.0000

Data Index: 1681051 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.1793. Min Act: -0.0000

Data Index: 367829 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3348. Min Act: -0.0000

Data Index: 1471350 (The Pile)

Max Activating Token Index: 933

Text #18

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.3239. Min Act: -0.0000

Data Index: 1759746 (The Pile)

Max Activating Token Index: 394

Text #19

Max Range: 1.7594. Min Range: -1.7594

Max Act: 1.2530. Min Act: -0.0000

Data Index: 998800 (The Pile)

Max Activating Token Index: 685