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

Dataset: The Pile

Neuron 4761 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4869. Min Act: -0.0000

Data Index: 1366725 (The Pile)

Max Activating Token Index: 413

Text #1

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4912. Min Act: -0.0000

Data Index: 924717 (The Pile)

Max Activating Token Index: 227

Text #2

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3914. Min Act: -0.0000

Data Index: 334973 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4341. Min Act: -0.0000

Data Index: 705296 (The Pile)

Max Activating Token Index: 515

Text #4

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4144. Min Act: -0.0000

Data Index: 1773843 (The Pile)

Max Activating Token Index: 201

Text #5

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3333. Min Act: -0.0000

Data Index: 270773 (The Pile)

Max Activating Token Index: 734

Text #6

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3738. Min Act: -0.0000

Data Index: 1752599 (The Pile)

Max Activating Token Index: 135

Text #7

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4057. Min Act: -0.0000

Data Index: 437739 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3612. Min Act: -0.0000

Data Index: 1799778 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3676. Min Act: -0.0000

Data Index: 81856 (The Pile)

Max Activating Token Index: 830

Text #10

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.4172. Min Act: -0.0000

Data Index: 1332391 (The Pile)

Max Activating Token Index: 964

Text #11

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3735. Min Act: -0.0000

Data Index: 955170 (The Pile)

Max Activating Token Index: 176

Text #12

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3523. Min Act: -0.0000

Data Index: 569901 (The Pile)

Max Activating Token Index: 580

Text #13

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3826. Min Act: -0.0000

Data Index: 1603490 (The Pile)

Max Activating Token Index: 483

Text #14

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3758. Min Act: -0.0000

Data Index: 1043957 (The Pile)

Max Activating Token Index: 246

Text #15

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3151. Min Act: -0.0000

Data Index: 1115474 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3797. Min Act: -0.0000

Data Index: 1141049 (The Pile)

Max Activating Token Index: 916

Text #17

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3502. Min Act: -0.0000

Data Index: 1814060 (The Pile)

Max Activating Token Index: 528

Text #18

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.3648. Min Act: -0.0000

Data Index: 73227 (The Pile)

Max Activating Token Index: 927

Text #19

Max Range: 0.4912. Min Range: -0.4912

Max Act: 0.2925. Min Act: -0.0000

Data Index: 1732678 (The Pile)

Max Activating Token Index: 155