Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1525 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1437. Min Range: -6.1437
Max Act: 6.1437. Min Act: -0.1700
Data Index: 6794220 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1437. Min Range: -6.1437
Max Act: 6.0812. Min Act: -0.1700
Data Index: 8639160 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1437. Min Range: -6.1437
Max Act: 6.0187. Min Act: -0.1700
Data Index: 8449383 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.9249. Min Act: -0.1700
Data Index: 4507983 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.9562. Min Act: -0.1700
Data Index: 8078336 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.9249. Min Act: -0.1700
Data Index: 4353232 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.9249. Min Act: -0.1700
Data Index: 8260421 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.8937. Min Act: -0.1700
Data Index: 4478855 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.8312. Min Act: -0.1700
Data Index: 1494689 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.8312. Min Act: -0.1700
Data Index: 891500 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.8312. Min Act: -0.1700
Data Index: 7258351 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7999. Min Act: -0.1700
Data Index: 7850953 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7999. Min Act: -0.1700
Data Index: 6269991 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7999. Min Act: -0.1700
Data Index: 5535810 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7687. Min Act: -0.1700
Data Index: 3927131 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7687. Min Act: -0.1700
Data Index: 64816 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7687. Min Act: -0.1700
Data Index: 8146359 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7999. Min Act: -0.1700
Data Index: 8691547 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7687. Min Act: -0.1700
Data Index: 2581513 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1437. Min Range: -6.1437
Max Act: 5.7374. Min Act: -0.1700
Data Index: 5460251 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19