Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 941 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7035. Min Act: -0.0000

Data Index: 1379926 (The Pile)

Max Activating Token Index: 140

Text #1

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.7377. Min Act: -0.0000

Data Index: 829101 (The Pile)

Max Activating Token Index: 380

Text #2

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.6552. Min Act: -0.0000

Data Index: 1881542 (The Pile)

Max Activating Token Index: 733

Text #3

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1134087 (The Pile)

Max Activating Token Index: 836

Text #4

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5827. Min Act: 0.0000

Data Index: 1655615 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5753. Min Act: -0.0000

Data Index: 1130971 (The Pile)

Max Activating Token Index: 371

Text #6

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5865. Min Act: -0.0000

Data Index: 1854939 (The Pile)

Max Activating Token Index: 172

Text #7

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5653. Min Act: -0.0000

Data Index: 245660 (The Pile)

Max Activating Token Index: 654

Text #8

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5839. Min Act: -0.0000

Data Index: 981080 (The Pile)

Max Activating Token Index: 193

Text #9

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5437. Min Act: -0.0000

Data Index: 587346 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5416. Min Act: -0.0000

Data Index: 580469 (The Pile)

Max Activating Token Index: 478

Text #11

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5599. Min Act: -0.0000

Data Index: 1880627 (The Pile)

Max Activating Token Index: 458

Text #12

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5119. Min Act: -0.0000

Data Index: 970205 (The Pile)

Max Activating Token Index: 445

Text #13

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5267. Min Act: -0.0000

Data Index: 1534061 (The Pile)

Max Activating Token Index: 396

Text #14

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5205. Min Act: -0.0000

Data Index: 309546 (The Pile)

Max Activating Token Index: 437

Text #15

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5506. Min Act: -0.0000

Data Index: 1493031 (The Pile)

Max Activating Token Index: 601

Text #16

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5040. Min Act: -0.0000

Data Index: 1578404 (The Pile)

Max Activating Token Index: 772

Text #17

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5133. Min Act: -0.0000

Data Index: 1923875 (The Pile)

Max Activating Token Index: 705

Text #18

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.5248. Min Act: -0.0000

Data Index: 1412768 (The Pile)

Max Activating Token Index: 372

Text #19

Max Range: 0.7377. Min Range: -0.7377

Max Act: 0.4952. Min Act: -0.0000

Data Index: 554144 (The Pile)

Max Activating Token Index: 912