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

Dataset: The Pile

Neuron 1949 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: 1.1391. Min Range: -1.1391

Max Act: 1.1391. Min Act: -0.0000

Data Index: 1331641 (The Pile)

Max Activating Token Index: 421

Text #1

Max Range: 1.1391. Min Range: -1.1391

Max Act: 1.0152. Min Act: -0.0000

Data Index: 1397381 (The Pile)

Max Activating Token Index: 804

Text #2

Max Range: 1.1391. Min Range: -1.1391

Max Act: 1.0493. Min Act: -0.0000

Data Index: 1608215 (The Pile)

Max Activating Token Index: 498

Text #3

Max Range: 1.1391. Min Range: -1.1391

Max Act: 1.0810. Min Act: -0.0000

Data Index: 336884 (The Pile)

Max Activating Token Index: 698

Text #4

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8971. Min Act: -0.0000

Data Index: 447598 (The Pile)

Max Activating Token Index: 845

Text #5

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.9800. Min Act: -0.0000

Data Index: 1778601 (The Pile)

Max Activating Token Index: 549

Text #6

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8481. Min Act: -0.0000

Data Index: 298560 (The Pile)

Max Activating Token Index: 14

Text #7

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8190. Min Act: -0.0000

Data Index: 1303363 (The Pile)

Max Activating Token Index: 490

Text #8

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7688. Min Act: -0.0000

Data Index: 1193637 (The Pile)

Max Activating Token Index: 713

Text #9

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7549. Min Act: -0.0000

Data Index: 1106904 (The Pile)

Max Activating Token Index: 158

Text #10

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.9280. Min Act: -0.0000

Data Index: 1977020 (The Pile)

Max Activating Token Index: 706

Text #11

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7598. Min Act: -0.0000

Data Index: 826957 (The Pile)

Max Activating Token Index: 37

Text #12

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7640. Min Act: -0.0000

Data Index: 168191 (The Pile)

Max Activating Token Index: 217

Text #13

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7168. Min Act: -0.0000

Data Index: 638354 (The Pile)

Max Activating Token Index: 991

Text #14

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8012. Min Act: -0.0000

Data Index: 582034 (The Pile)

Max Activating Token Index: 56

Text #15

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7492. Min Act: -0.0000

Data Index: 1631608 (The Pile)

Max Activating Token Index: 253

Text #16

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.7626. Min Act: -0.0000

Data Index: 1296363 (The Pile)

Max Activating Token Index: 254

Text #17

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1932963 (The Pile)

Max Activating Token Index: 552

Text #18

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.6990. Min Act: -0.0000

Data Index: 1708435 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.1391. Min Range: -1.1391

Max Act: 0.8107. Min Act: -0.0000

Data Index: 1448846 (The Pile)

Max Activating Token Index: 773