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

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

Neuron 113 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: 3.4422. Min Range: -3.4422

Max Act: 3.4422. Min Act: -0.1700

Data Index: 1283211 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.4422. Min Act: -0.1700

Data Index: 1641578 (Python Code)

Max Activating Token Index: 603

Text #2

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.3794. Min Act: -0.1700

Data Index: 1621773 (Python Code)

Max Activating Token Index: 271

Text #3

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.3166. Min Act: -0.1700

Data Index: 2910 (C4 (Web Text))

Max Activating Token Index: 95

Text #4

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2852. Min Act: -0.1700

Data Index: 1545969 (Python Code)

Max Activating Token Index: 914

Text #5

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1522382 (Python Code)

Max Activating Token Index: 469

Text #6

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2538. Min Act: -0.1700

Data Index: 1475442 (Python Code)

Max Activating Token Index: 117

Text #7

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2852. Min Act: -0.1700

Data Index: 1486792 (Python Code)

Max Activating Token Index: 406

Text #8

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2538. Min Act: -0.1700

Data Index: 1572834 (Python Code)

Max Activating Token Index: 931

Text #9

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2538. Min Act: -0.1700

Data Index: 1418513 (Python Code)

Max Activating Token Index: 721

Text #10

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.1909. Min Act: -0.1700

Data Index: 1436961 (Python Code)

Max Activating Token Index: 89

Text #11

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.1909. Min Act: -0.1700

Data Index: 1419116 (Python Code)

Max Activating Token Index: 694

Text #12

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.1909. Min Act: -0.1699

Data Index: 1409880 (Python Code)

Max Activating Token Index: 831

Text #13

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1374665 (Python Code)

Max Activating Token Index: 778

Text #14

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1593338 (Python Code)

Max Activating Token Index: 563

Text #15

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1565903 (Python Code)

Max Activating Token Index: 291

Text #16

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.2224. Min Act: -0.1700

Data Index: 1555079 (Python Code)

Max Activating Token Index: 285

Text #17

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.1594. Min Act: -0.1700

Data Index: 1457926 (Python Code)

Max Activating Token Index: 640

Text #18

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.1909. Min Act: -0.1700

Data Index: 1467740 (Python Code)

Max Activating Token Index: 607

Text #19

Max Range: 3.4422. Min Range: -3.4422

Max Act: 3.1909. Min Act: -0.1700

Data Index: 1394460 (Python Code)

Max Activating Token Index: 315