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

Dataset: The Pile

Neuron 1829 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.6542. Min Act: -0.0000

Data Index: 46238 (The Pile)

Max Activating Token Index: 415

Text #1

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.4035. Min Act: -0.0000

Data Index: 1731575 (The Pile)

Max Activating Token Index: 647

Text #2

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3131. Min Act: -0.0000

Data Index: 1910634 (The Pile)

Max Activating Token Index: 961

Text #3

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.2839. Min Act: -0.0000

Data Index: 468226 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.4270. Min Act: -0.0000

Data Index: 399946 (The Pile)

Max Activating Token Index: 514

Text #5

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3832. Min Act: -0.0000

Data Index: 590512 (The Pile)

Max Activating Token Index: 234

Text #6

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.3654. Min Act: -0.0000

Data Index: 531356 (The Pile)

Max Activating Token Index: 954

Text #7

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.1659. Min Act: -0.0000

Data Index: 1873415 (The Pile)

Max Activating Token Index: 407

Text #8

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.2799. Min Act: -0.0000

Data Index: 1513551 (The Pile)

Max Activating Token Index: 749

Text #9

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.1157. Min Act: -0.0000

Data Index: 465617 (The Pile)

Max Activating Token Index: 776

Text #10

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.2634. Min Act: -0.0000

Data Index: 688754 (The Pile)

Max Activating Token Index: 437

Text #11

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.2342. Min Act: -0.0000

Data Index: 84274 (The Pile)

Max Activating Token Index: 818

Text #12

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.1067. Min Act: -0.0000

Data Index: 1730022 (The Pile)

Max Activating Token Index: 288

Text #13

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.2092. Min Act: -0.0000

Data Index: 6929 (The Pile)

Max Activating Token Index: 441

Text #14

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.0682. Min Act: -0.0000

Data Index: 1442493 (The Pile)

Max Activating Token Index: 112

Text #15

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.1304. Min Act: -0.0000

Data Index: 1281111 (The Pile)

Max Activating Token Index: 330

Text #16

Max Range: 3.6542. Min Range: -3.6542

Max Act: 2.9764. Min Act: -0.0000

Data Index: 1987450 (The Pile)

Max Activating Token Index: 867

Text #17

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.1588. Min Act: -0.0000

Data Index: 1180672 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.1588. Min Act: -0.0000

Data Index: 1397303 (The Pile)

Max Activating Token Index: 515

Text #19

Max Range: 3.6542. Min Range: -3.6542

Max Act: 3.0015. Min Act: -0.0000

Data Index: 394907 (The Pile)

Max Activating Token Index: 460