Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2812 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.4468. Min Act: -0.1700
Data Index: 7389762 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.3531. Min Act: -0.1700
Data Index: 2165139 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.2281. Min Act: -0.1700
Data Index: 4999887 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.2281. Min Act: -0.1700
Data Index: 3857376 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.1968. Min Act: -0.1700
Data Index: 3456668 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.1343. Min Act: -0.1700
Data Index: 1493793 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.1343. Min Act: -0.1700
Data Index: 3134483 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0718. Min Act: -0.1700
Data Index: 361862 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0718. Min Act: -0.1700
Data Index: 6353668 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0718. Min Act: -0.1700
Data Index: 6092508 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0406. Min Act: -0.1700
Data Index: 570712 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0093. Min Act: -0.1700
Data Index: 119814 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9781. Min Act: -0.1700
Data Index: 3355684 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4468. Min Range: -6.4468
Max Act: 6.0093. Min Act: -0.1700
Data Index: 1958453 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9781. Min Act: -0.1700
Data Index: 5223625 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9468. Min Act: -0.1700
Data Index: 1060835 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9781. Min Act: -0.1700
Data Index: 8597545 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9156. Min Act: -0.1700
Data Index: 7569058 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.9468. Min Act: -0.1700
Data Index: 4802615 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4468. Min Range: -6.4468
Max Act: 5.8843. Min Act: -0.1700
Data Index: 3867428 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #19