Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2191 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.8201. Min Act: -0.1700
Data Index: 6549885 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.6326. Min Act: -0.1700
Data Index: 7736973 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.6326. Min Act: -0.1700
Data Index: 838318 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.5076. Min Act: -0.1700
Data Index: 7621107 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.4451. Min Act: -0.1700
Data Index: 2122107 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.3826. Min Act: -0.1700
Data Index: 5889144 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.3201. Min Act: -0.1700
Data Index: 4645208 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.3201. Min Act: -0.1700
Data Index: 1296324 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.3201. Min Act: -0.1700
Data Index: 7170104 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.3201. Min Act: -0.1700
Data Index: 441822 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.3201. Min Act: -0.1700
Data Index: 2571451 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.3201. Min Act: -0.1700
Data Index: 6106370 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.2576. Min Act: -0.1700
Data Index: 242209 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.1951. Min Act: -0.1700
Data Index: 2278104 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.1951. Min Act: -0.1700
Data Index: 5501619 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.1951. Min Act: -0.1700
Data Index: 1087676 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.1326. Min Act: -0.1700
Data Index: 5479382 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.1326. Min Act: -0.1700
Data Index: 3006524 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.1326. Min Act: -0.1700
Data Index: 2892373 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8201. Min Range: -9.8201
Max Act: 9.1326. Min Act: -0.1700
Data Index: 2856684 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #19