Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2743 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.1655. Min Act: -0.1700
Data Index: 217370 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.1343. Min Act: -0.1700
Data Index: 7846729 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.1030. Min Act: -0.1700
Data Index: 7986301 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.1030. Min Act: -0.1700
Data Index: 6926767 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0718. Min Act: -0.1700
Data Index: 8778957 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0718. Min Act: -0.1700
Data Index: 2190272 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0405. Min Act: -0.1700
Data Index: 3476674 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0405. Min Act: -0.1700
Data Index: 6131918 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0718. Min Act: -0.1700
Data Index: 7720662 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0405. Min Act: -0.1700
Data Index: 7846727 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0405. Min Act: -0.1700
Data Index: 2692320 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0405. Min Act: -0.1700
Data Index: 191346 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0093. Min Act: -0.1700
Data Index: 2093496 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1655. Min Range: -5.1655
Max Act: 4.9780. Min Act: -0.1700
Data Index: 6385784 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0093. Min Act: -0.1700
Data Index: 162072 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1655. Min Range: -5.1655
Max Act: 5.0093. Min Act: -0.1700
Data Index: 217371 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1655. Min Range: -5.1655
Max Act: 4.9468. Min Act: -0.1700
Data Index: 6691100 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1655. Min Range: -5.1655
Max Act: 4.9780. Min Act: -0.1700
Data Index: 2110089 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1655. Min Range: -5.1655
Max Act: 4.9780. Min Act: -0.1700
Data Index: 7846726 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1655. Min Range: -5.1655
Max Act: 4.9468. Min Act: -0.1700
Data Index: 7743310 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #19