Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1330 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7852. Min Range: -9.7852
Max Act: 9.7852. Min Act: -0.1700
Data Index: 1433280 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7852. Min Range: -9.7852
Max Act: 9.1602. Min Act: -0.1700
Data Index: 4857335 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7852. Min Range: -9.7852
Max Act: 9.0352. Min Act: -0.1700
Data Index: 4931231 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.9727. Min Act: -0.1700
Data Index: 8520044 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.9102. Min Act: -0.1700
Data Index: 4229252 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.9102. Min Act: -0.1700
Data Index: 741162 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.9102. Min Act: -0.1700
Data Index: 4980797 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.9102. Min Act: -0.1700
Data Index: 5817848 (Open Web Text)
Max Activating Token Index: 240
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.9102. Min Act: -0.1700
Data Index: 7977807 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.8477. Min Act: -0.1700
Data Index: 3986018 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.7852. Min Act: -0.1700
Data Index: 1816645 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.7227. Min Act: -0.1700
Data Index: 704278 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.7227. Min Act: -0.1700
Data Index: 6429230 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.7227. Min Act: -0.1700
Data Index: 8126253 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.6602. Min Act: -0.1700
Data Index: 6991284 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.6602. Min Act: -0.1700
Data Index: 6593477 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.5977. Min Act: -0.1700
Data Index: 820254 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.5977. Min Act: -0.1700
Data Index: 10389 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.5977. Min Act: -0.1700
Data Index: 5750737 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7852. Min Range: -9.7852
Max Act: 8.5977. Min Act: -0.1700
Data Index: 2961579 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #19