Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5563 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0928. Min Act: -0.1700
Data Index: 5153249 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0616. Min Act: -0.1700
Data Index: 6865861 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0303. Min Act: -0.1700
Data Index: 1337300 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0303. Min Act: -0.1700
Data Index: 6937790 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0616. Min Act: -0.1700
Data Index: 2830885 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0303. Min Act: -0.1700
Data Index: 2589294 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0303. Min Act: -0.1700
Data Index: 1428966 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0303. Min Act: -0.1700
Data Index: 2442922 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0303. Min Act: -0.1700
Data Index: 2460169 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9991. Min Act: -0.1700
Data Index: 8669812 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9991. Min Act: -0.1700
Data Index: 4272923 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9991. Min Act: -0.1700
Data Index: 7245215 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9991. Min Act: -0.1700
Data Index: 8649851 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9991. Min Act: -0.1700
Data Index: 765628 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0928. Min Range: -5.0928
Max Act: 5.0303. Min Act: -0.1700
Data Index: 7907667 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9678. Min Act: -0.1700
Data Index: 2583616 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9678. Min Act: -0.1700
Data Index: 3491565 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9678. Min Act: -0.1700
Data Index: 945802 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9678. Min Act: -0.1700
Data Index: 5235235 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0928. Min Range: -5.0928
Max Act: 4.9678. Min Act: -0.1700
Data Index: 2438965 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #19