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

Dataset: The Pile

Neuron 3465 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: 0.7933. Min Range: -0.7933

Max Act: 0.7933. Min Act: -0.0000

Data Index: 1320019 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1810205 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7485. Min Act: -0.0000

Data Index: 253768 (The Pile)

Max Activating Token Index: 89

Text #3

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7755. Min Act: -0.0000

Data Index: 1673620 (The Pile)

Max Activating Token Index: 315

Text #4

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6890. Min Act: -0.0000

Data Index: 1386470 (The Pile)

Max Activating Token Index: 635

Text #5

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7046. Min Act: -0.0000

Data Index: 7150 (The Pile)

Max Activating Token Index: 185

Text #6

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6890. Min Act: -0.0000

Data Index: 783052 (The Pile)

Max Activating Token Index: 429

Text #7

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.7195. Min Act: -0.0000

Data Index: 1632162 (The Pile)

Max Activating Token Index: 136

Text #8

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6734. Min Act: -0.0000

Data Index: 1538434 (The Pile)

Max Activating Token Index: 573

Text #9

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6944. Min Act: -0.0000

Data Index: 1316757 (The Pile)

Max Activating Token Index: 238

Text #10

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6801. Min Act: -0.0000

Data Index: 458447 (The Pile)

Max Activating Token Index: 24

Text #11

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6382. Min Act: -0.0000

Data Index: 1142540 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6716. Min Act: -0.0000

Data Index: 1796421 (The Pile)

Max Activating Token Index: 950

Text #13

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.5936. Min Act: -0.0000

Data Index: 798745 (The Pile)

Max Activating Token Index: 827

Text #14

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6687. Min Act: -0.0000

Data Index: 1868145 (The Pile)

Max Activating Token Index: 29

Text #15

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6465. Min Act: -0.0000

Data Index: 1876817 (The Pile)

Max Activating Token Index: 547

Text #16

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6268. Min Act: -0.0000

Data Index: 547487 (The Pile)

Max Activating Token Index: 715

Text #17

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6469. Min Act: -0.0000

Data Index: 1839686 (The Pile)

Max Activating Token Index: 640

Text #18

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6895. Min Act: -0.0000

Data Index: 743607 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 0.7933. Min Range: -0.7933

Max Act: 0.6344. Min Act: -0.0000

Data Index: 719339 (The Pile)

Max Activating Token Index: 344