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

Dataset: The Pile

Neuron 2013 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.5583. Min Act: -0.0000

Data Index: 892551 (The Pile)

Max Activating Token Index: 313

Text #1

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.5731. Min Act: -0.0000

Data Index: 971549 (The Pile)

Max Activating Token Index: 268

Text #2

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3892. Min Act: -0.0000

Data Index: 1249711 (The Pile)

Max Activating Token Index: 768

Text #3

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1456916 (The Pile)

Max Activating Token Index: 183

Text #4

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.4762. Min Act: -0.0000

Data Index: 973847 (The Pile)

Max Activating Token Index: 432

Text #5

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3891. Min Act: -0.0000

Data Index: 1090813 (The Pile)

Max Activating Token Index: 200

Text #6

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2129. Min Act: -0.0000

Data Index: 1186337 (The Pile)

Max Activating Token Index: 691

Text #7

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3179. Min Act: -0.0000

Data Index: 1081518 (The Pile)

Max Activating Token Index: 427

Text #8

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0352. Min Act: -0.0000

Data Index: 586232 (The Pile)

Max Activating Token Index: 272

Text #9

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1880. Min Act: -0.0000

Data Index: 994397 (The Pile)

Max Activating Token Index: 774

Text #10

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.2169. Min Act: -0.0000

Data Index: 947754 (The Pile)

Max Activating Token Index: 853

Text #11

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1519. Min Act: -0.0000

Data Index: 371282 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.3597. Min Act: -0.0000

Data Index: 521168 (The Pile)

Max Activating Token Index: 431

Text #13

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1656. Min Act: -0.0000

Data Index: 1229851 (The Pile)

Max Activating Token Index: 786

Text #14

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1145. Min Act: -0.0000

Data Index: 1489760 (The Pile)

Max Activating Token Index: 388

Text #15

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0737. Min Act: -0.0000

Data Index: 775971 (The Pile)

Max Activating Token Index: 328

Text #16

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0839. Min Act: -0.0000

Data Index: 192536 (The Pile)

Max Activating Token Index: 325

Text #17

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.1637. Min Act: -0.0000

Data Index: 130020 (The Pile)

Max Activating Token Index: 356

Text #18

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0947. Min Act: -0.0000

Data Index: 617378 (The Pile)

Max Activating Token Index: 526

Text #19

Max Range: 1.5731. Min Range: -1.5731

Max Act: 1.0686. Min Act: -0.0000

Data Index: 1858858 (The Pile)

Max Activating Token Index: 38