Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3673 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.3718. Min Act: -0.1700
Data Index: 6728843 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.3406. Min Act: -0.1700
Data Index: 4716117 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.3406. Min Act: -0.1700
Data Index: 5145787 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.3093. Min Act: -0.1700
Data Index: 7390259 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2468. Min Act: -0.1700
Data Index: 2923315 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2468. Min Act: -0.1700
Data Index: 6375063 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2156. Min Act: -0.1700
Data Index: 4694993 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2468. Min Act: -0.1700
Data Index: 648738 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2468. Min Act: -0.1700
Data Index: 948381 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2156. Min Act: -0.1700
Data Index: 468012 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2156. Min Act: -0.1700
Data Index: 2915362 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2468. Min Act: -0.1700
Data Index: 2588563 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.2156. Min Act: -0.1700
Data Index: 4854432 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.1843. Min Act: -0.1700
Data Index: 5015883 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.1531. Min Act: -0.1700
Data Index: 1407165 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.1843. Min Act: -0.1700
Data Index: 996816 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.1531. Min Act: -0.1700
Data Index: 6353670 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.1218. Min Act: -0.1700
Data Index: 3129868 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.1843. Min Act: -0.1700
Data Index: 4587442 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3718. Min Range: -5.3718
Max Act: 5.1218. Min Act: -0.1700
Data Index: 5524770 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #19