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

Dataset: The Pile

Neuron 977 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.0785. Min Range: -3.0785

Max Act: 3.0785. Min Act: -0.0000

Data Index: 1721118 (The Pile)

Max Activating Token Index: 279

Text #1

Max Range: 3.0785. Min Range: -3.0785

Max Act: 3.0755. Min Act: -0.0000

Data Index: 718250 (The Pile)

Max Activating Token Index: 269

Text #2

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.8046. Min Act: -0.0000

Data Index: 1876417 (The Pile)

Max Activating Token Index: 458

Text #3

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.6655. Min Act: -0.0000

Data Index: 1007639 (The Pile)

Max Activating Token Index: 439

Text #4

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.4015. Min Act: -0.0000

Data Index: 120939 (The Pile)

Max Activating Token Index: 128

Text #5

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.6973. Min Act: -0.0000

Data Index: 550108 (The Pile)

Max Activating Token Index: 521

Text #6

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.6930. Min Act: -0.0000

Data Index: 843739 (The Pile)

Max Activating Token Index: 201

Text #7

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.5921. Min Act: -0.0000

Data Index: 1916441 (The Pile)

Max Activating Token Index: 392

Text #8

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.4403. Min Act: -0.0000

Data Index: 92732 (The Pile)

Max Activating Token Index: 680

Text #9

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.2451. Min Act: -0.0000

Data Index: 767490 (The Pile)

Max Activating Token Index: 311

Text #10

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.1091. Min Act: -0.0000

Data Index: 767024 (The Pile)

Max Activating Token Index: 841

Text #11

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.3565. Min Act: -0.0000

Data Index: 1791580 (The Pile)

Max Activating Token Index: 419

Text #12

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.3148. Min Act: -0.0000

Data Index: 1255483 (The Pile)

Max Activating Token Index: 517

Text #13

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.3043. Min Act: -0.0000

Data Index: 1044844 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.0591. Min Act: -0.0000

Data Index: 1933314 (The Pile)

Max Activating Token Index: 554

Text #15

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.2925. Min Act: -0.0000

Data Index: 1297202 (The Pile)

Max Activating Token Index: 777

Text #16

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.2808. Min Act: -0.0000

Data Index: 1845071 (The Pile)

Max Activating Token Index: 315

Text #17

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.1309. Min Act: -0.0000

Data Index: 1857413 (The Pile)

Max Activating Token Index: 337

Text #18

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.2280. Min Act: -0.0000

Data Index: 958738 (The Pile)

Max Activating Token Index: 470

Text #19

Max Range: 3.0785. Min Range: -3.0785

Max Act: 2.0561. Min Act: -0.0000

Data Index: 819812 (The Pile)

Max Activating Token Index: 320