Model: GELU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 1813 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-2l')

Text #0

Max Range: 4.1038. Min Range: -4.1038

Max Act: 4.1038. Min Act: -0.1700

Data Index: 729138 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.8537. Min Act: -0.1700

Data Index: 242603 (C4 (Web Text))

Max Activating Token Index: 395

Text #2

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.8224. Min Act: -0.1700

Data Index: 640190 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.8224. Min Act: -0.1700

Data Index: 1181672 (C4 (Web Text))

Max Activating Token Index: 805

Text #4

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.7598. Min Act: -0.1700

Data Index: 49479 (C4 (Web Text))

Max Activating Token Index: 211

Text #5

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.8224. Min Act: -0.1700

Data Index: 594706 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.7911. Min Act: -0.1700

Data Index: 913264 (C4 (Web Text))

Max Activating Token Index: 189

Text #7

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.7598. Min Act: -0.1700

Data Index: 495937 (C4 (Web Text))

Max Activating Token Index: 554

Text #8

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.7598. Min Act: -0.1700

Data Index: 424732 (C4 (Web Text))

Max Activating Token Index: 350

Text #9

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.7598. Min Act: -0.1700

Data Index: 645283 (C4 (Web Text))

Max Activating Token Index: 225

Text #10

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.7286. Min Act: -0.1700

Data Index: 145829 (C4 (Web Text))

Max Activating Token Index: 721

Text #11

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.6973. Min Act: -0.1700

Data Index: 194690 (C4 (Web Text))

Max Activating Token Index: 738

Text #12

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.6973. Min Act: -0.1700

Data Index: 1037674 (C4 (Web Text))

Max Activating Token Index: 436

Text #13

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.7286. Min Act: -0.1700

Data Index: 353298 (C4 (Web Text))

Max Activating Token Index: 714

Text #14

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.6973. Min Act: -0.1700

Data Index: 945198 (C4 (Web Text))

Max Activating Token Index: 194

Text #15

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.6973. Min Act: -0.1700

Data Index: 547867 (C4 (Web Text))

Max Activating Token Index: 825

Text #16

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.6660. Min Act: -0.1700

Data Index: 1054473 (C4 (Web Text))

Max Activating Token Index: 482

Text #17

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.6973. Min Act: -0.1700

Data Index: 633775 (C4 (Web Text))

Max Activating Token Index: 343

Text #18

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.6660. Min Act: -0.1700

Data Index: 412939 (C4 (Web Text))

Max Activating Token Index: 290

Text #19

Max Range: 4.1038. Min Range: -4.1038

Max Act: 3.6973. Min Act: -0.1700

Data Index: 453270 (C4 (Web Text))

Max Activating Token Index: 434