Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2043 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.1120. Min Act: -0.1700
Data Index: 5754265 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0945. Min Act: -0.1700
Data Index: 1276893 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0858. Min Act: -0.1700
Data Index: 6110693 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0770. Min Act: -0.1700
Data Index: 8801524 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0770. Min Act: -0.1700
Data Index: 4834518 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0770. Min Act: -0.1700
Data Index: 1791384 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0683. Min Act: -0.1700
Data Index: 113453 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0683. Min Act: -0.1700
Data Index: 7785181 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0596. Min Act: -0.1700
Data Index: 7026260 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0596. Min Act: -0.1700
Data Index: 4831841 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0683. Min Act: -0.1700
Data Index: 6261575 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0596. Min Act: -0.1700
Data Index: 209133 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0508. Min Act: -0.1700
Data Index: 7554302 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0596. Min Act: -0.1700
Data Index: 1647735 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0508. Min Act: -0.1700
Data Index: 2765015 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0421. Min Act: -0.1700
Data Index: 8728735 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0421. Min Act: -0.1700
Data Index: 27745 (Open Web Text)
Max Activating Token Index: 875
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0421. Min Act: -0.1700
Data Index: 295131 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0334. Min Act: -0.1700
Data Index: 6170306 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.1120. Min Range: -1.1120
Max Act: 1.0421. Min Act: -0.1700
Data Index: 1416315 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #19