Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4022 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0079. Min Range: -3.0079
Max Act: 3.0079. Min Act: -0.1700
Data Index: 8076129 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8813. Min Act: -0.1700
Data Index: 1624712 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8654. Min Act: -0.1700
Data Index: 5014714 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8654. Min Act: -0.1700
Data Index: 3735212 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8495. Min Act: -0.1700
Data Index: 5151600 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8495. Min Act: -0.1700
Data Index: 3830647 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8495. Min Act: -0.1700
Data Index: 2087849 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8495. Min Act: -0.1700
Data Index: 3685459 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8495. Min Act: -0.1700
Data Index: 5548537 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8336. Min Act: -0.1700
Data Index: 2204280 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8336. Min Act: -0.1700
Data Index: 4497481 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8336. Min Act: -0.1700
Data Index: 8415864 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8336. Min Act: -0.1700
Data Index: 1624708 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8018. Min Act: -0.1700
Data Index: 2510718 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8177. Min Act: -0.1700
Data Index: 4004305 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8177. Min Act: -0.1700
Data Index: 3681245 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8177. Min Act: -0.1700
Data Index: 7104251 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8018. Min Act: -0.1700
Data Index: 1782395 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8018. Min Act: -0.1700
Data Index: 6202088 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0079. Min Range: -3.0079
Max Act: 2.8177. Min Act: -0.1700
Data Index: 710180 (Open Web Text)
Max Activating Token Index: 22
Click toggle to see full text
Truncated
Full Text #19