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

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

Neuron 948 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.9113. Min Act: -0.1700

Data Index: 66631 (C4 (Web Text))

Max Activating Token Index: 782

Text #1

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.6301. Min Act: -0.1700

Data Index: 916513 (C4 (Web Text))

Max Activating Token Index: 632

Text #2

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.2863. Min Act: -0.1700

Data Index: 30496 (C4 (Web Text))

Max Activating Token Index: 121

Text #3

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.1926. Min Act: -0.1700

Data Index: 29665 (C4 (Web Text))

Max Activating Token Index: 558

Text #4

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.1926. Min Act: -0.1700

Data Index: 383711 (C4 (Web Text))

Max Activating Token Index: 907

Text #5

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.1301. Min Act: -0.1700

Data Index: 1301950 (C4 (Web Text))

Max Activating Token Index: 683

Text #6

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 890966 (C4 (Web Text))

Max Activating Token Index: 817

Text #7

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.1613. Min Act: -0.1700

Data Index: 1196119 (C4 (Web Text))

Max Activating Token Index: 278

Text #8

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.1926. Min Act: -0.1700

Data Index: 671130 (C4 (Web Text))

Max Activating Token Index: 64

Text #9

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 782370 (C4 (Web Text))

Max Activating Token Index: 112

Text #10

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.1926. Min Act: -0.1700

Data Index: 146818 (C4 (Web Text))

Max Activating Token Index: 463

Text #11

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.1301. Min Act: -0.1700

Data Index: 930327 (C4 (Web Text))

Max Activating Token Index: 442

Text #12

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0676. Min Act: -0.1700

Data Index: 1240294 (C4 (Web Text))

Max Activating Token Index: 844

Text #13

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 717047 (C4 (Web Text))

Max Activating Token Index: 356

Text #14

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 882286 (C4 (Web Text))

Max Activating Token Index: 363

Text #15

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 757459 (C4 (Web Text))

Max Activating Token Index: 867

Text #16

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0988. Min Act: -0.1700

Data Index: 440931 (C4 (Web Text))

Max Activating Token Index: 665

Text #17

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0676. Min Act: -0.1700

Data Index: 853963 (C4 (Web Text))

Max Activating Token Index: 824

Text #18

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.0363. Min Act: -0.1700

Data Index: 268201 (C4 (Web Text))

Max Activating Token Index: 577

Text #19

Max Range: 5.9113. Min Range: -5.9113

Max Act: 5.1301. Min Act: -0.1700

Data Index: 1128291 (C4 (Web Text))

Max Activating Token Index: 632