Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3329 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.9957. Min Act: -0.1700
Data Index: 2163601 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.4332. Min Act: -0.1700
Data Index: 7034389 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9957. Min Range: -6.9957
Max Act: 6.3082. Min Act: -0.1700
Data Index: 965951 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9957. Min Act: -0.1700
Data Index: 8236465 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9644. Min Act: -0.1700
Data Index: 1438329 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9644. Min Act: -0.1700
Data Index: 1422945 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9644. Min Act: -0.1700
Data Index: 5659416 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9332. Min Act: -0.1700
Data Index: 6618398 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9332. Min Act: -0.1700
Data Index: 5715907 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9019. Min Act: -0.1700
Data Index: 8014706 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9332. Min Act: -0.1700
Data Index: 3624431 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.9019. Min Act: -0.1700
Data Index: 8161974 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.8707. Min Act: -0.1700
Data Index: 231212 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.8707. Min Act: -0.1700
Data Index: 3426318 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.8394. Min Act: -0.1700
Data Index: 1917456 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.8394. Min Act: -0.1700
Data Index: 7787280 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.8394. Min Act: -0.1700
Data Index: 3564296 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.8082. Min Act: -0.1700
Data Index: 6579439 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.8082. Min Act: -0.1700
Data Index: 26790 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9957. Min Range: -6.9957
Max Act: 5.8082. Min Act: -0.1700
Data Index: 7455143 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19