Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1578 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.7581. Min Act: -0.1700
Data Index: 6425159 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.6956. Min Act: -0.1700
Data Index: 3024706 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.3831. Min Act: -0.1700
Data Index: 2256112 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.3831. Min Act: -0.1700
Data Index: 4062675 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.2581. Min Act: -0.1700
Data Index: 4009118 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.1956. Min Act: -0.1700
Data Index: 6450835 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.0081. Min Act: -0.1700
Data Index: 2447743 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.0081. Min Act: -0.1700
Data Index: 8571034 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.0081. Min Act: -0.1700
Data Index: 5293269 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.0081. Min Act: -0.1700
Data Index: 4518121 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7581. Min Range: -9.7581
Max Act: 9.0081. Min Act: -0.1700
Data Index: 1998549 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.9456. Min Act: -0.1700
Data Index: 3592886 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.9456. Min Act: -0.1700
Data Index: 4111423 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.8831. Min Act: -0.1700
Data Index: 2687110 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.7581. Min Act: -0.1700
Data Index: 1519028 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.7581. Min Act: -0.1700
Data Index: 6331931 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.8206. Min Act: -0.1700
Data Index: 3753894 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.8206. Min Act: -0.1700
Data Index: 4154142 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.7581. Min Act: -0.1700
Data Index: 1503790 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7581. Min Range: -9.7581
Max Act: 8.7581. Min Act: -0.1700
Data Index: 1961136 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #19