Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2059 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')

Text #0

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5564. Min Act: -0.0001

Data Index: 96619 (The Pile)

Max Activating Token Index: 383

Text #1

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5693. Min Act: -0.0000

Data Index: 1074839 (The Pile)

Max Activating Token Index: 457

Text #2

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5501. Min Act: -0.0000

Data Index: 1182980 (The Pile)

Max Activating Token Index: 676

Text #3

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5153. Min Act: -0.0000

Data Index: 107541 (The Pile)

Max Activating Token Index: 700

Text #4

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.5002. Min Act: -0.0000

Data Index: 105735 (The Pile)

Max Activating Token Index: 725

Text #5

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4702. Min Act: -0.0000

Data Index: 532570 (The Pile)

Max Activating Token Index: 785

Text #6

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4925. Min Act: -0.0000

Data Index: 468267 (The Pile)

Max Activating Token Index: 475

Text #7

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4285. Min Act: -0.0000

Data Index: 1633166 (The Pile)

Max Activating Token Index: 200

Text #8

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4898. Min Act: -0.0000

Data Index: 743937 (The Pile)

Max Activating Token Index: 214

Text #9

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4424. Min Act: -0.0000

Data Index: 789640 (The Pile)

Max Activating Token Index: 203

Text #10

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4184. Min Act: -0.0000

Data Index: 401803 (The Pile)

Max Activating Token Index: 990

Text #11

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4723. Min Act: -0.0000

Data Index: 1082184 (The Pile)

Max Activating Token Index: 453

Text #12

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4861. Min Act: -0.0000

Data Index: 709704 (The Pile)

Max Activating Token Index: 734

Text #13

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4938. Min Act: -0.0000

Data Index: 1159795 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4649. Min Act: -0.0001

Data Index: 1545026 (The Pile)

Max Activating Token Index: 908

Text #15

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4344. Min Act: -0.0000

Data Index: 1856557 (The Pile)

Max Activating Token Index: 763

Text #16

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4595. Min Act: -0.0000

Data Index: 1101142 (The Pile)

Max Activating Token Index: 357

Text #17

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4612. Min Act: -0.0000

Data Index: 750391 (The Pile)

Max Activating Token Index: 215

Text #18

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4600. Min Act: -0.0000

Data Index: 973588 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 0.5693. Min Range: -0.5693

Max Act: 0.4132. Min Act: -0.0000

Data Index: 1100244 (The Pile)

Max Activating Token Index: 143