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

Dataset: The Pile

Neuron 1807 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3368. Min Act: -0.0000

Data Index: 1117917 (The Pile)

Max Activating Token Index: 519

Text #1

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.3716. Min Act: -0.0000

Data Index: 1976843 (The Pile)

Max Activating Token Index: 610

Text #2

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.2082. Min Act: -0.0000

Data Index: 949042 (The Pile)

Max Activating Token Index: 588

Text #3

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1778. Min Act: -0.0000

Data Index: 1514814 (The Pile)

Max Activating Token Index: 624

Text #4

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1089. Min Act: -0.0000

Data Index: 1939837 (The Pile)

Max Activating Token Index: 255

Text #5

Max Range: 1.3716. Min Range: -1.3716

Max Act: 1.1287. Min Act: -0.0000

Data Index: 190550 (The Pile)

Max Activating Token Index: 500

Text #6

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.8551. Min Act: -0.0000

Data Index: 1172422 (The Pile)

Max Activating Token Index: 554

Text #7

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.8954. Min Act: -0.0000

Data Index: 1055388 (The Pile)

Max Activating Token Index: 687

Text #8

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9018. Min Act: -0.0000

Data Index: 104711 (The Pile)

Max Activating Token Index: 40

Text #9

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.8637. Min Act: -0.0000

Data Index: 1392622 (The Pile)

Max Activating Token Index: 681

Text #10

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.8331. Min Act: -0.0000

Data Index: 609608 (The Pile)

Max Activating Token Index: 377

Text #11

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.9121. Min Act: -0.0000

Data Index: 1734075 (The Pile)

Max Activating Token Index: 951

Text #12

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.8227. Min Act: -0.0000

Data Index: 1067519 (The Pile)

Max Activating Token Index: 227

Text #13

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.7999. Min Act: -0.0000

Data Index: 395580 (The Pile)

Max Activating Token Index: 354

Text #14

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1064067 (The Pile)

Max Activating Token Index: 466

Text #15

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.7628. Min Act: -0.0000

Data Index: 440821 (The Pile)

Max Activating Token Index: 397

Text #16

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.6931. Min Act: -0.0000

Data Index: 570852 (The Pile)

Max Activating Token Index: 984

Text #17

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.7536. Min Act: -0.0000

Data Index: 13328 (The Pile)

Max Activating Token Index: 728

Text #18

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.8089. Min Act: -0.0000

Data Index: 1537898 (The Pile)

Max Activating Token Index: 142

Text #19

Max Range: 1.3716. Min Range: -1.3716

Max Act: 0.8351. Min Act: -0.0000

Data Index: 55122 (The Pile)

Max Activating Token Index: 881