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

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

Neuron 27 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.9168. Min Act: -0.1700

Data Index: 1047717 (C4 (Web Text))

Max Activating Token Index: 164

Text #1

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8856. Min Act: -0.1700

Data Index: 519806 (C4 (Web Text))

Max Activating Token Index: 170

Text #2

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.9168. Min Act: -0.1700

Data Index: 34982 (C4 (Web Text))

Max Activating Token Index: 309

Text #3

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8856. Min Act: -0.1700

Data Index: 429510 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8856. Min Act: -0.1700

Data Index: 463826 (C4 (Web Text))

Max Activating Token Index: 363

Text #5

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8856. Min Act: -0.1700

Data Index: 747216 (C4 (Web Text))

Max Activating Token Index: 1010

Text #6

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8543. Min Act: -0.1700

Data Index: 64156 (C4 (Web Text))

Max Activating Token Index: 752

Text #7

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8543. Min Act: -0.1700

Data Index: 614866 (C4 (Web Text))

Max Activating Token Index: 650

Text #8

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8230. Min Act: -0.1700

Data Index: 1190139 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8543. Min Act: -0.1700

Data Index: 853334 (C4 (Web Text))

Max Activating Token Index: 874

Text #10

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8230. Min Act: -0.1700

Data Index: 1267037 (C4 (Web Text))

Max Activating Token Index: 42

Text #11

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8230. Min Act: -0.1700

Data Index: 1289672 (C4 (Web Text))

Max Activating Token Index: 721

Text #12

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7917. Min Act: -0.1700

Data Index: 938705 (C4 (Web Text))

Max Activating Token Index: 865

Text #13

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7917. Min Act: -0.1700

Data Index: 1283151 (C4 (Web Text))

Max Activating Token Index: 434

Text #14

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7604. Min Act: -0.1700

Data Index: 179038 (C4 (Web Text))

Max Activating Token Index: 851

Text #15

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8230. Min Act: -0.1700

Data Index: 1289916 (C4 (Web Text))

Max Activating Token Index: 347

Text #16

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.8230. Min Act: -0.1700

Data Index: 662442 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7917. Min Act: -0.1700

Data Index: 618165 (C4 (Web Text))

Max Activating Token Index: 943

Text #18

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7604. Min Act: -0.1700

Data Index: 486409 (C4 (Web Text))

Max Activating Token Index: 725

Text #19

Max Range: 3.9168. Min Range: -3.9168

Max Act: 3.7604. Min Act: -0.1700

Data Index: 404658 (C4 (Web Text))

Max Activating Token Index: 740