Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 160 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6139. Min Range: -9.6139
Max Act: 9.6139. Min Act: -0.1700
Data Index: 1517575 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6139. Min Range: -9.6139
Max Act: 9.3639. Min Act: -0.1700
Data Index: 1667276 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6139. Min Range: -9.6139
Max Act: 9.3639. Min Act: -0.1700
Data Index: 2615869 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6139. Min Range: -9.6139
Max Act: 9.1139. Min Act: -0.1700
Data Index: 8237585 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6139. Min Range: -9.6139
Max Act: 9.1139. Min Act: -0.1700
Data Index: 255953 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6139. Min Range: -9.6139
Max Act: 9.1139. Min Act: -0.1700
Data Index: 2497151 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6139. Min Range: -9.6139
Max Act: 9.0514. Min Act: -0.1700
Data Index: 5379129 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.9889. Min Act: -0.1700
Data Index: 4193458 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.9264. Min Act: -0.1700
Data Index: 7815447 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.9264. Min Act: -0.1700
Data Index: 3598350 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.9264. Min Act: -0.1700
Data Index: 1755597 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.9889. Min Act: -0.1700
Data Index: 8318290 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.9264. Min Act: -0.1700
Data Index: 2942153 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.9264. Min Act: -0.1700
Data Index: 2808171 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.8639. Min Act: -0.1700
Data Index: 1783762 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.8014. Min Act: -0.1700
Data Index: 6575545 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.8014. Min Act: -0.1700
Data Index: 8449357 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.7389. Min Act: -0.1700
Data Index: 3518957 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.7389. Min Act: -0.1700
Data Index: 4069175 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6139. Min Range: -9.6139
Max Act: 8.6764. Min Act: -0.1700
Data Index: 2147391 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19