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

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

Neuron 592 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: 5.1126. Min Range: -5.1126

Max Act: 5.0813. Min Act: -0.1700

Data Index: 149607 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 5.1126. Min Range: -5.1126

Max Act: 5.1126. Min Act: -0.1700

Data Index: 964061 (C4 (Web Text))

Max Activating Token Index: 31

Text #2

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.7688. Min Act: -0.1700

Data Index: 402205 (C4 (Web Text))

Max Activating Token Index: 772

Text #3

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.8313. Min Act: -0.1700

Data Index: 814142 (C4 (Web Text))

Max Activating Token Index: 476

Text #4

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.7376. Min Act: -0.1700

Data Index: 1273017 (C4 (Web Text))

Max Activating Token Index: 746

Text #5

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.7063. Min Act: -0.1700

Data Index: 803171 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.7376. Min Act: -0.1700

Data Index: 113379 (C4 (Web Text))

Max Activating Token Index: 754

Text #7

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.6438. Min Act: -0.1700

Data Index: 565293 (C4 (Web Text))

Max Activating Token Index: 308

Text #8

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.6751. Min Act: -0.1700

Data Index: 613366 (C4 (Web Text))

Max Activating Token Index: 383

Text #9

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.5813. Min Act: -0.1700

Data Index: 1157255 (C4 (Web Text))

Max Activating Token Index: 837

Text #10

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.6126. Min Act: -0.1700

Data Index: 622128 (C4 (Web Text))

Max Activating Token Index: 725

Text #11

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.5501. Min Act: -0.1700

Data Index: 521500 (C4 (Web Text))

Max Activating Token Index: 848

Text #12

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.4876. Min Act: -0.1700

Data Index: 1079112 (C4 (Web Text))

Max Activating Token Index: 252

Text #13

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.4876. Min Act: -0.1700

Data Index: 462080 (C4 (Web Text))

Max Activating Token Index: 950

Text #14

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.4876. Min Act: -0.1700

Data Index: 60963 (C4 (Web Text))

Max Activating Token Index: 643

Text #15

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.4251. Min Act: -0.1700

Data Index: 1263491 (C4 (Web Text))

Max Activating Token Index: 447

Text #16

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.5188. Min Act: -0.1700

Data Index: 400006 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.5501. Min Act: -0.1700

Data Index: 1212471 (C4 (Web Text))

Max Activating Token Index: 931

Text #18

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.5188. Min Act: -0.1700

Data Index: 1355308 (C4 (Web Text))

Max Activating Token Index: 479

Text #19

Max Range: 5.1126. Min Range: -5.1126

Max Act: 4.4876. Min Act: -0.1700

Data Index: 365737 (C4 (Web Text))

Max Activating Token Index: 906