Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 756 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2078. Min Range: -4.2078
Max Act: 4.2078. Min Act: -0.1700
Data Index: 4824774 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2078. Min Range: -4.2078
Max Act: 4.0827. Min Act: -0.1700
Data Index: 3617454 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2078. Min Range: -4.2078
Max Act: 4.0827. Min Act: -0.1700
Data Index: 4844369 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9890. Min Act: -0.1700
Data Index: 2087900 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2078. Min Range: -4.2078
Max Act: 4.0202. Min Act: -0.1700
Data Index: 1489127 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9577. Min Act: -0.1700
Data Index: 1835732 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9577. Min Act: -0.1700
Data Index: 7861614 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9264. Min Act: -0.1700
Data Index: 8661493 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9264. Min Act: -0.1700
Data Index: 360312 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.9264. Min Act: -0.1700
Data Index: 4105195 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8952. Min Act: -0.1700
Data Index: 4555548 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8639. Min Act: -0.1700
Data Index: 5471824 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8952. Min Act: -0.1700
Data Index: 4350903 (Open Web Text)
Max Activating Token Index: 427
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8639. Min Act: -0.1700
Data Index: 5970654 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8326. Min Act: -0.1700
Data Index: 1278467 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8639. Min Act: -0.1700
Data Index: 5937847 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8952. Min Act: -0.1700
Data Index: 8068793 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8326. Min Act: -0.1700
Data Index: 1774178 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8326. Min Act: -0.1700
Data Index: 3171105 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2078. Min Range: -4.2078
Max Act: 3.8014. Min Act: -0.1700
Data Index: 816704 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19