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

Dataset: The Pile

Neuron 4033 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: 1.7418. Min Range: -1.7418

Max Act: 1.6562. Min Act: -0.0000

Data Index: 982952 (The Pile)

Max Activating Token Index: 428

Text #1

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5339. Min Act: -0.0000

Data Index: 308942 (The Pile)

Max Activating Token Index: 961

Text #2

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5590. Min Act: -0.0000

Data Index: 790115 (The Pile)

Max Activating Token Index: 522

Text #3

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.7418. Min Act: -0.0000

Data Index: 1534326 (The Pile)

Max Activating Token Index: 607

Text #4

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5137. Min Act: -0.0000

Data Index: 850232 (The Pile)

Max Activating Token Index: 924

Text #5

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.4771. Min Act: -0.0000

Data Index: 263980 (The Pile)

Max Activating Token Index: 585

Text #6

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5977. Min Act: -0.0000

Data Index: 572368 (The Pile)

Max Activating Token Index: 417

Text #7

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.6380. Min Act: -0.0000

Data Index: 651195 (The Pile)

Max Activating Token Index: 221

Text #8

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.4875. Min Act: -0.0000

Data Index: 361375 (The Pile)

Max Activating Token Index: 383

Text #9

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5187. Min Act: -0.0000

Data Index: 1363819 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5246. Min Act: -0.0000

Data Index: 947353 (The Pile)

Max Activating Token Index: 363

Text #11

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5215. Min Act: -0.0000

Data Index: 830427 (The Pile)

Max Activating Token Index: 225

Text #12

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.7044. Min Act: -0.0000

Data Index: 693063 (The Pile)

Max Activating Token Index: 772

Text #13

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.4800. Min Act: -0.0000

Data Index: 1685150 (The Pile)

Max Activating Token Index: 426

Text #14

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.4391. Min Act: -0.0000

Data Index: 1534858 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.3874. Min Act: -0.0000

Data Index: 1390656 (The Pile)

Max Activating Token Index: 265

Text #16

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5044. Min Act: -0.0000

Data Index: 1851954 (The Pile)

Max Activating Token Index: 600

Text #17

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.5016. Min Act: -0.0000

Data Index: 858938 (The Pile)

Max Activating Token Index: 551

Text #18

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.4515. Min Act: -0.0000

Data Index: 1167980 (The Pile)

Max Activating Token Index: 269

Text #19

Max Range: 1.7418. Min Range: -1.7418

Max Act: 1.3576. Min Act: -0.0000

Data Index: 635463 (The Pile)

Max Activating Token Index: 258