Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2824 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.6751. Min Range: -7.6751
Max Act: 7.6751. Min Act: -0.1700
Data Index: 1414771 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.6751. Min Range: -7.6751
Max Act: 7.6439. Min Act: -0.1700
Data Index: 1414770 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.6751. Min Range: -7.6751
Max Act: 7.1126. Min Act: -0.1700
Data Index: 6859498 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.6751. Min Range: -7.6751
Max Act: 7.0189. Min Act: -0.1700
Data Index: 1507711 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.9251. Min Act: -0.1700
Data Index: 3379861 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.8626. Min Act: -0.1700
Data Index: 7316889 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.8939. Min Act: -0.1700
Data Index: 849093 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.8626. Min Act: -0.1700
Data Index: 373040 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.8314. Min Act: -0.1700
Data Index: 4359653 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.8626. Min Act: -0.1700
Data Index: 2014571 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.7689. Min Act: -0.1700
Data Index: 3238883 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.7376. Min Act: -0.1700
Data Index: 6859497 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.7689. Min Act: -0.1700
Data Index: 183679 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.7376. Min Act: -0.1700
Data Index: 7705307 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.6751. Min Act: -0.1700
Data Index: 2360561 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.6439. Min Act: -0.1700
Data Index: 251976 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.6439. Min Act: -0.1700
Data Index: 5883923 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.6126. Min Act: -0.1700
Data Index: 5545951 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.6126. Min Act: -0.1700
Data Index: 4151548 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.6751. Min Range: -7.6751
Max Act: 6.5814. Min Act: -0.1700
Data Index: 8722624 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #19