Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4875 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4457. Min Range: -9.4457
Max Act: 9.4457. Min Act: -0.1700
Data Index: 7129712 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4457. Min Range: -9.4457
Max Act: 9.2582. Min Act: -0.1700
Data Index: 5387771 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4457. Min Range: -9.4457
Max Act: 9.1957. Min Act: -0.1700
Data Index: 7238553 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.9457. Min Act: -0.1700
Data Index: 222869 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.8832. Min Act: -0.1700
Data Index: 5853538 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.8207. Min Act: -0.1700
Data Index: 3399069 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.7582. Min Act: -0.1700
Data Index: 6906504 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.7582. Min Act: -0.1700
Data Index: 582500 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6957. Min Act: -0.1700
Data Index: 5555990 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.7582. Min Act: -0.1700
Data Index: 7717437 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.7582. Min Act: -0.1700
Data Index: 8364147 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6957. Min Act: -0.1700
Data Index: 3376988 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6957. Min Act: -0.1700
Data Index: 7081705 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6957. Min Act: -0.1700
Data Index: 8215130 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6957. Min Act: -0.1700
Data Index: 2559644 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6957. Min Act: -0.1700
Data Index: 2177191 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6332. Min Act: -0.1700
Data Index: 536463 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6332. Min Act: -0.1700
Data Index: 2639654 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.6332. Min Act: -0.1700
Data Index: 5132086 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4457. Min Range: -9.4457
Max Act: 8.5707. Min Act: -0.1700
Data Index: 2882180 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #19