Model: GELU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2038 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.1403. Min Range: -3.1403

Max Act: 3.1403. Min Act: -0.1700

Data Index: 1647275 (Python Code)

Max Activating Token Index: 926

Text #1

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.9825. Min Act: -0.1700

Data Index: 857290 (C4 (Web Text))

Max Activating Token Index: 529

Text #2

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.9825. Min Act: -0.1700

Data Index: 337379 (C4 (Web Text))

Max Activating Token Index: 754

Text #3

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8716. Min Act: -0.1700

Data Index: 498796 (C4 (Web Text))

Max Activating Token Index: 108

Text #4

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8874. Min Act: -0.1700

Data Index: 1648371 (Python Code)

Max Activating Token Index: 71

Text #5

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8874. Min Act: -0.1700

Data Index: 1174638 (C4 (Web Text))

Max Activating Token Index: 800

Text #6

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8239. Min Act: -0.1700

Data Index: 142718 (C4 (Web Text))

Max Activating Token Index: 818

Text #7

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8716. Min Act: -0.1700

Data Index: 1025375 (C4 (Web Text))

Max Activating Token Index: 312

Text #8

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8557. Min Act: -0.1700

Data Index: 749570 (C4 (Web Text))

Max Activating Token Index: 652

Text #9

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8874. Min Act: -0.1700

Data Index: 719604 (C4 (Web Text))

Max Activating Token Index: 396

Text #10

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.7122. Min Act: -0.1700

Data Index: 1291917 (C4 (Web Text))

Max Activating Token Index: 680

Text #11

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.7761. Min Act: -0.1700

Data Index: 743617 (C4 (Web Text))

Max Activating Token Index: 187

Text #12

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.7920. Min Act: -0.1700

Data Index: 967864 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8716. Min Act: -0.1700

Data Index: 275192 (C4 (Web Text))

Max Activating Token Index: 861

Text #14

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8080. Min Act: -0.1700

Data Index: 393581 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8398. Min Act: -0.1700

Data Index: 190632 (C4 (Web Text))

Max Activating Token Index: 809

Text #16

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8557. Min Act: -0.1700

Data Index: 749233 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.8080. Min Act: -0.1700

Data Index: 191384 (C4 (Web Text))

Max Activating Token Index: 506

Text #18

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.7602. Min Act: -0.1700

Data Index: 955397 (C4 (Web Text))

Max Activating Token Index: 865

Text #19

Max Range: 3.1403. Min Range: -3.1403

Max Act: 2.7761. Min Act: -0.1700

Data Index: 943330 (C4 (Web Text))

Max Activating Token Index: 486