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

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

Neuron 228 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: 5.8125. Min Range: -5.8125

Max Act: 5.8125. Min Act: -0.1700

Data Index: 1181789 (C4 (Web Text))

Max Activating Token Index: 701

Text #1

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.7500. Min Act: -0.1700

Data Index: 101310 (C4 (Web Text))

Max Activating Token Index: 621

Text #2

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.7500. Min Act: -0.1700

Data Index: 483151 (C4 (Web Text))

Max Activating Token Index: 445

Text #3

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.6563. Min Act: -0.1700

Data Index: 900967 (C4 (Web Text))

Max Activating Token Index: 150

Text #4

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.5938. Min Act: -0.1700

Data Index: 1044054 (C4 (Web Text))

Max Activating Token Index: 286

Text #5

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.5625. Min Act: -0.1700

Data Index: 456196 (C4 (Web Text))

Max Activating Token Index: 662

Text #6

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.5625. Min Act: -0.1700

Data Index: 4939 (C4 (Web Text))

Max Activating Token Index: 344

Text #7

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.5625. Min Act: -0.1700

Data Index: 549891 (C4 (Web Text))

Max Activating Token Index: 385

Text #8

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.5000. Min Act: -0.1700

Data Index: 21260 (C4 (Web Text))

Max Activating Token Index: 100

Text #9

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.4688. Min Act: -0.1700

Data Index: 432533 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3750. Min Act: -0.1700

Data Index: 210312 (C4 (Web Text))

Max Activating Token Index: 140

Text #11

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3438. Min Act: -0.1700

Data Index: 1050670 (C4 (Web Text))

Max Activating Token Index: 802

Text #12

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3750. Min Act: -0.1700

Data Index: 1054415 (C4 (Web Text))

Max Activating Token Index: 608

Text #13

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3438. Min Act: -0.1700

Data Index: 1139848 (C4 (Web Text))

Max Activating Token Index: 966

Text #14

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3750. Min Act: -0.1700

Data Index: 41144 (C4 (Web Text))

Max Activating Token Index: 440

Text #15

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3438. Min Act: -0.1700

Data Index: 208359 (C4 (Web Text))

Max Activating Token Index: 960

Text #16

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3438. Min Act: -0.1700

Data Index: 654109 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.4063. Min Act: -0.1700

Data Index: 877450 (C4 (Web Text))

Max Activating Token Index: 521

Text #18

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3750. Min Act: -0.1700

Data Index: 382770 (C4 (Web Text))

Max Activating Token Index: 559

Text #19

Max Range: 5.8125. Min Range: -5.8125

Max Act: 5.3125. Min Act: -0.1700

Data Index: 560668 (C4 (Web Text))

Max Activating Token Index: 254