Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3137 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.3346. Min Act: -0.1700
Data Index: 6593150 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.2096. Min Act: -0.1700
Data Index: 2856557 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.2096. Min Act: -0.1700
Data Index: 861057 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.2096. Min Act: -0.1700
Data Index: 5657198 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.2096. Min Act: -0.1700
Data Index: 2289866 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.1471. Min Act: -0.1700
Data Index: 2485599 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.0846. Min Act: -0.1700
Data Index: 6841184 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.0846. Min Act: -0.1700
Data Index: 502179 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.0221. Min Act: -0.1700
Data Index: 4728172 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.0221. Min Act: -0.1700
Data Index: 1930403 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.0221. Min Act: -0.1700
Data Index: 5346388 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.0221. Min Act: -0.1700
Data Index: 8212427 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3346. Min Range: -8.3346
Max Act: 8.0221. Min Act: -0.1700
Data Index: 4152947 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3346. Min Range: -8.3346
Max Act: 7.9596. Min Act: -0.1700
Data Index: 1817612 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3346. Min Range: -8.3346
Max Act: 7.9596. Min Act: -0.1700
Data Index: 5098856 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3346. Min Range: -8.3346
Max Act: 7.8971. Min Act: -0.1700
Data Index: 2432336 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3346. Min Range: -8.3346
Max Act: 7.8971. Min Act: -0.1700
Data Index: 6252116 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3346. Min Range: -8.3346
Max Act: 7.8971. Min Act: -0.1700
Data Index: 1496454 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3346. Min Range: -8.3346
Max Act: 7.8971. Min Act: -0.1700
Data Index: 1511436 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3346. Min Range: -8.3346
Max Act: 7.8971. Min Act: -0.1700
Data Index: 755756 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #19