Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1070 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.0687. Min Range: -4.0687
Max Act: 4.0687. Min Act: -0.1700
Data Index: 6046236 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0687. Min Range: -4.0687
Max Act: 4.0375. Min Act: -0.1700
Data Index: 6798987 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0687. Min Range: -4.0687
Max Act: 4.0062. Min Act: -0.1700
Data Index: 8644888 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.9437. Min Act: -0.1700
Data Index: 8644893 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.9437. Min Act: -0.1700
Data Index: 1745186 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.9750. Min Act: -0.1700
Data Index: 5026611 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8968. Min Act: -0.1700
Data Index: 5541064 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.9124. Min Act: -0.1700
Data Index: 1299803 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8968. Min Act: -0.1700
Data Index: 185177 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8968. Min Act: -0.1700
Data Index: 1071504 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8968. Min Act: -0.1700
Data Index: 560743 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8968. Min Act: -0.1700
Data Index: 1461110 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8812. Min Act: -0.1700
Data Index: 1071505 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8812. Min Act: -0.1700
Data Index: 5330774 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8968. Min Act: -0.1700
Data Index: 1071506 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8968. Min Act: -0.1700
Data Index: 4730431 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8812. Min Act: -0.1700
Data Index: 85060 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8968. Min Act: -0.1700
Data Index: 1915083 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8655. Min Act: -0.1700
Data Index: 6601800 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0687. Min Range: -4.0687
Max Act: 3.8655. Min Act: -0.1700
Data Index: 356700 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #19