Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5072 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1533. Min Range: -5.1533
Max Act: 5.1533. Min Act: -0.1700
Data Index: 7445067 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1533. Min Range: -5.1533
Max Act: 5.0283. Min Act: -0.1700
Data Index: 2520086 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.9658. Min Act: -0.1700
Data Index: 335774 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.9658. Min Act: -0.1700
Data Index: 6670536 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.9345. Min Act: -0.1700
Data Index: 1108301 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.9033. Min Act: -0.1700
Data Index: 8011250 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.9033. Min Act: -0.1700
Data Index: 4904103 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8720. Min Act: -0.1700
Data Index: 7797568 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8408. Min Act: -0.1700
Data Index: 2855406 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8720. Min Act: -0.1700
Data Index: 1754521 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8408. Min Act: -0.1700
Data Index: 2656292 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8408. Min Act: -0.1700
Data Index: 4245372 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8408. Min Act: -0.1700
Data Index: 3650526 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8408. Min Act: -0.1700
Data Index: 8427269 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8095. Min Act: -0.1700
Data Index: 1476716 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8095. Min Act: -0.1700
Data Index: 7449241 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8095. Min Act: -0.1700
Data Index: 3650528 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.7783. Min Act: -0.1700
Data Index: 2084702 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8095. Min Act: -0.1700
Data Index: 6107319 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1533. Min Range: -5.1533
Max Act: 4.8095. Min Act: -0.1700
Data Index: 3082583 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19