Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3018 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1557. Min Range: -8.1557
Max Act: 8.1557. Min Act: -0.1700
Data Index: 6420839 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.9682. Min Act: -0.1700
Data Index: 4859634 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.5620. Min Act: -0.1700
Data Index: 7079913 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.3432. Min Act: -0.1700
Data Index: 6575252 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.2807. Min Act: -0.1700
Data Index: 6823246 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.2807. Min Act: -0.1700
Data Index: 2639057 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.2495. Min Act: -0.1700
Data Index: 2639048 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.1557. Min Act: -0.1700
Data Index: 7025171 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.0932. Min Act: -0.1700
Data Index: 326138 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.0620. Min Act: -0.1700
Data Index: 4652042 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.0307. Min Act: -0.1700
Data Index: 415292 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1557. Min Range: -8.1557
Max Act: 7.0307. Min Act: -0.1700
Data Index: 6464001 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1557. Min Range: -8.1557
Max Act: 6.9995. Min Act: -0.1700
Data Index: 907349 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1557. Min Range: -8.1557
Max Act: 6.9995. Min Act: -0.1700
Data Index: 3656033 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1557. Min Range: -8.1557
Max Act: 6.9370. Min Act: -0.1700
Data Index: 3471928 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1557. Min Range: -8.1557
Max Act: 6.9682. Min Act: -0.1700
Data Index: 1207273 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1557. Min Range: -8.1557
Max Act: 6.9995. Min Act: -0.1700
Data Index: 5843108 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1557. Min Range: -8.1557
Max Act: 6.9057. Min Act: -0.1700
Data Index: 537880 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1557. Min Range: -8.1557
Max Act: 6.8745. Min Act: -0.1700
Data Index: 5339042 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1557. Min Range: -8.1557
Max Act: 6.9057. Min Act: -0.1700
Data Index: 5326029 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #19