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

Dataset: The Pile

Neuron 5055 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: 1.1058. Min Range: -1.1058

Max Act: 1.1058. Min Act: -0.0000

Data Index: 659823 (The Pile)

Max Activating Token Index: 49

Text #1

Max Range: 1.1058. Min Range: -1.1058

Max Act: 1.0827. Min Act: -0.0000

Data Index: 772521 (The Pile)

Max Activating Token Index: 586

Text #2

Max Range: 1.1058. Min Range: -1.1058

Max Act: 1.0515. Min Act: -0.0000

Data Index: 1391767 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8880. Min Act: -0.0000

Data Index: 642313 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.9970. Min Act: -0.0000

Data Index: 824824 (The Pile)

Max Activating Token Index: 550

Text #5

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.9403. Min Act: -0.0000

Data Index: 600059 (The Pile)

Max Activating Token Index: 563

Text #6

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.9227. Min Act: -0.0000

Data Index: 930453 (The Pile)

Max Activating Token Index: 560

Text #7

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8460. Min Act: -0.0000

Data Index: 1013973 (The Pile)

Max Activating Token Index: 358

Text #8

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7535. Min Act: -0.0000

Data Index: 1400846 (The Pile)

Max Activating Token Index: 181

Text #9

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8290. Min Act: -0.0000

Data Index: 1227348 (The Pile)

Max Activating Token Index: 370

Text #10

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8412. Min Act: -0.0000

Data Index: 1729996 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7550. Min Act: -0.0000

Data Index: 1265982 (The Pile)

Max Activating Token Index: 845

Text #12

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1684173 (The Pile)

Max Activating Token Index: 729

Text #13

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.6911. Min Act: -0.0000

Data Index: 1168986 (The Pile)

Max Activating Token Index: 327

Text #14

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8264. Min Act: -0.0000

Data Index: 1766308 (The Pile)

Max Activating Token Index: 236

Text #15

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1203108 (The Pile)

Max Activating Token Index: 679

Text #16

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7025. Min Act: -0.0000

Data Index: 1560332 (The Pile)

Max Activating Token Index: 176

Text #17

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.8388. Min Act: -0.0000

Data Index: 1694494 (The Pile)

Max Activating Token Index: 691

Text #18

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7988. Min Act: -0.0000

Data Index: 1521767 (The Pile)

Max Activating Token Index: 149

Text #19

Max Range: 1.1058. Min Range: -1.1058

Max Act: 0.7060. Min Act: -0.0000

Data Index: 1227478 (The Pile)

Max Activating Token Index: 43