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

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

Neuron 1821 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: 5.9438. Min Range: -5.9438

Max Act: 5.9438. Min Act: -0.1700

Data Index: 603057 (C4 (Web Text))

Max Activating Token Index: 949

Text #1

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.7250. Min Act: -0.1700

Data Index: 587116 (C4 (Web Text))

Max Activating Token Index: 654

Text #2

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.6938. Min Act: -0.1700

Data Index: 196677 (C4 (Web Text))

Max Activating Token Index: 873

Text #3

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.6938. Min Act: -0.1700

Data Index: 47088 (C4 (Web Text))

Max Activating Token Index: 974

Text #4

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.6313. Min Act: -0.1700

Data Index: 935608 (C4 (Web Text))

Max Activating Token Index: 659

Text #5

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.6000. Min Act: -0.1700

Data Index: 190431 (C4 (Web Text))

Max Activating Token Index: 944

Text #6

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5063. Min Act: -0.1700

Data Index: 575742 (C4 (Web Text))

Max Activating Token Index: 591

Text #7

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5375. Min Act: -0.1700

Data Index: 953112 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5688. Min Act: -0.1700

Data Index: 1179289 (C4 (Web Text))

Max Activating Token Index: 1006

Text #9

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5688. Min Act: -0.1700

Data Index: 780907 (C4 (Web Text))

Max Activating Token Index: 201

Text #10

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.4438. Min Act: -0.1700

Data Index: 1246150 (C4 (Web Text))

Max Activating Token Index: 809

Text #11

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5375. Min Act: -0.1700

Data Index: 1261374 (C4 (Web Text))

Max Activating Token Index: 171

Text #12

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5375. Min Act: -0.1700

Data Index: 259481 (C4 (Web Text))

Max Activating Token Index: 185

Text #13

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.4438. Min Act: -0.1700

Data Index: 1316675 (C4 (Web Text))

Max Activating Token Index: 738

Text #14

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5063. Min Act: -0.1700

Data Index: 853597 (C4 (Web Text))

Max Activating Token Index: 119

Text #15

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.4750. Min Act: -0.1700

Data Index: 798691 (C4 (Web Text))

Max Activating Token Index: 882

Text #16

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.4438. Min Act: -0.1700

Data Index: 820999 (C4 (Web Text))

Max Activating Token Index: 375

Text #17

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.6313. Min Act: -0.1700

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 725

Text #18

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5063. Min Act: -0.1700

Data Index: 471391 (C4 (Web Text))

Max Activating Token Index: 763

Text #19

Max Range: 5.9438. Min Range: -5.9438

Max Act: 5.5063. Min Act: -0.1700

Data Index: 638519 (C4 (Web Text))

Max Activating Token Index: 207