Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 557 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.3343. Min Act: -0.1700

Data Index: 706028 (C4 (Web Text))

Max Activating Token Index: 86

Text #1

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1780. Min Act: -0.1700

Data Index: 310279 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1468. Min Act: -0.1700

Data Index: 1319484 (C4 (Web Text))

Max Activating Token Index: 813

Text #3

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1780. Min Act: -0.1700

Data Index: 19839 (C4 (Web Text))

Max Activating Token Index: 332

Text #4

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1780. Min Act: -0.1700

Data Index: 236016 (C4 (Web Text))

Max Activating Token Index: 945

Text #5

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0843. Min Act: -0.1700

Data Index: 184396 (C4 (Web Text))

Max Activating Token Index: 310

Text #6

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0843. Min Act: -0.1700

Data Index: 441805 (C4 (Web Text))

Max Activating Token Index: 688

Text #7

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.1155. Min Act: -0.1700

Data Index: 59985 (C4 (Web Text))

Max Activating Token Index: 364

Text #8

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0843. Min Act: -0.1700

Data Index: 311562 (C4 (Web Text))

Max Activating Token Index: 327

Text #9

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0530. Min Act: -0.1700

Data Index: 1414371 (Python Code)

Max Activating Token Index: 1023

Text #10

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0530. Min Act: -0.1700

Data Index: 407261 (C4 (Web Text))

Max Activating Token Index: 230

Text #11

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0218. Min Act: -0.1700

Data Index: 314139 (C4 (Web Text))

Max Activating Token Index: 445

Text #12

Max Range: 5.3343. Min Range: -5.3343

Max Act: 4.9905. Min Act: -0.1700

Data Index: 339942 (C4 (Web Text))

Max Activating Token Index: 761

Text #13

Max Range: 5.3343. Min Range: -5.3343

Max Act: 4.9905. Min Act: -0.1700

Data Index: 1049385 (C4 (Web Text))

Max Activating Token Index: 423

Text #14

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0843. Min Act: -0.1700

Data Index: 820606 (C4 (Web Text))

Max Activating Token Index: 270

Text #15

Max Range: 5.3343. Min Range: -5.3343

Max Act: 4.9280. Min Act: -0.1700

Data Index: 791422 (C4 (Web Text))

Max Activating Token Index: 496

Text #16

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0530. Min Act: -0.1700

Data Index: 775134 (C4 (Web Text))

Max Activating Token Index: 349

Text #17

Max Range: 5.3343. Min Range: -5.3343

Max Act: 4.9593. Min Act: -0.1700

Data Index: 952877 (C4 (Web Text))

Max Activating Token Index: 149

Text #18

Max Range: 5.3343. Min Range: -5.3343

Max Act: 4.9593. Min Act: -0.1700

Data Index: 1018343 (C4 (Web Text))

Max Activating Token Index: 239

Text #19

Max Range: 5.3343. Min Range: -5.3343

Max Act: 5.0843. Min Act: -0.1700

Data Index: 435783 (C4 (Web Text))

Max Activating Token Index: 371