Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1440 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0019. Min Range: -6.0019
Max Act: 6.0019. Min Act: -0.1700
Data Index: 8771217 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.9394. Min Act: -0.1700
Data Index: 1706159 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.8144. Min Act: -0.1700
Data Index: 327353 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.8144. Min Act: -0.1700
Data Index: 6709026 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.7519. Min Act: -0.1700
Data Index: 8761175 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.7207. Min Act: -0.1700
Data Index: 1242987 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.7207. Min Act: -0.1700
Data Index: 1695301 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.6269. Min Act: -0.1700
Data Index: 3037561 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5957. Min Act: -0.1700
Data Index: 2713841 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5957. Min Act: -0.1700
Data Index: 8309827 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5957. Min Act: -0.1700
Data Index: 4977207 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5957. Min Act: -0.1700
Data Index: 8771216 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5644. Min Act: -0.1700
Data Index: 7669079 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5019. Min Act: -0.1700
Data Index: 7070143 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5332. Min Act: -0.1700
Data Index: 7374190 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5019. Min Act: -0.1700
Data Index: 5855319 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5019. Min Act: -0.1700
Data Index: 3687517 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.5019. Min Act: -0.1700
Data Index: 4189973 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.4707. Min Act: -0.1700
Data Index: 1869381 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0019. Min Range: -6.0019
Max Act: 5.4707. Min Act: -0.1700
Data Index: 3751466 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #19