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

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

Neuron 1566 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8548. Min Act: -0.1700

Data Index: 856974 (C4 (Web Text))

Max Activating Token Index: 933

Text #1

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8861. Min Act: -0.1700

Data Index: 807261 (C4 (Web Text))

Max Activating Token Index: 803

Text #2

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8548. Min Act: -0.1700

Data Index: 755513 (C4 (Web Text))

Max Activating Token Index: 555

Text #3

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8861. Min Act: -0.1700

Data Index: 448967 (C4 (Web Text))

Max Activating Token Index: 185

Text #4

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8235. Min Act: -0.1700

Data Index: 6085 (C4 (Web Text))

Max Activating Token Index: 107

Text #5

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1003389 (C4 (Web Text))

Max Activating Token Index: 157

Text #6

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8235. Min Act: -0.1700

Data Index: 459019 (C4 (Web Text))

Max Activating Token Index: 778

Text #7

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8235. Min Act: -0.1700

Data Index: 152200 (C4 (Web Text))

Max Activating Token Index: 55

Text #8

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8235. Min Act: -0.1700

Data Index: 481815 (C4 (Web Text))

Max Activating Token Index: 707

Text #9

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7923. Min Act: -0.1700

Data Index: 1261784 (C4 (Web Text))

Max Activating Token Index: 312

Text #10

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7923. Min Act: -0.1700

Data Index: 317731 (C4 (Web Text))

Max Activating Token Index: 790

Text #11

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8235. Min Act: -0.1700

Data Index: 1226216 (C4 (Web Text))

Max Activating Token Index: 884

Text #12

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.8235. Min Act: -0.1700

Data Index: 389674 (C4 (Web Text))

Max Activating Token Index: 644

Text #13

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7610. Min Act: -0.1700

Data Index: 563793 (C4 (Web Text))

Max Activating Token Index: 249

Text #14

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7923. Min Act: -0.1700

Data Index: 326484 (C4 (Web Text))

Max Activating Token Index: 118

Text #15

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7923. Min Act: -0.1700

Data Index: 1333877 (C4 (Web Text))

Max Activating Token Index: 295

Text #16

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7923. Min Act: -0.1700

Data Index: 1205104 (C4 (Web Text))

Max Activating Token Index: 760

Text #17

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7610. Min Act: -0.1700

Data Index: 972695 (C4 (Web Text))

Max Activating Token Index: 995

Text #18

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7453. Min Act: -0.1700

Data Index: 703023 (C4 (Web Text))

Max Activating Token Index: 989

Text #19

Max Range: 3.8861. Min Range: -3.8861

Max Act: 3.7297. Min Act: -0.1700

Data Index: 1034233 (C4 (Web Text))

Max Activating Token Index: 375