Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.6813. Min Act: -0.1700
Data Index: 6997800 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.3375. Min Act: -0.1700
Data Index: 3092300 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.2438. Min Act: -0.1700
Data Index: 4740674 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.2125. Min Act: -0.1700
Data Index: 4025885 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.1813. Min Act: -0.1700
Data Index: 360246 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.1500. Min Act: -0.1700
Data Index: 3031517 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.0250. Min Act: -0.1700
Data Index: 4142803 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.0250. Min Act: -0.1700
Data Index: 4435888 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6813. Min Range: -4.6813
Max Act: 4.0250. Min Act: -0.1700
Data Index: 2504742 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9937. Min Act: -0.1700
Data Index: 5789374 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9937. Min Act: -0.1700
Data Index: 2949865 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9937. Min Act: -0.1700
Data Index: 1110640 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9937. Min Act: -0.1700
Data Index: 3782127 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9625. Min Act: -0.1700
Data Index: 863380 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9312. Min Act: -0.1700
Data Index: 993489 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9625. Min Act: -0.1700
Data Index: 2396797 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9625. Min Act: -0.1700
Data Index: 2039482 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.9625. Min Act: -0.1700
Data Index: 6052111 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.8687. Min Act: -0.1700
Data Index: 3656871 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6813. Min Range: -4.6813
Max Act: 3.8999. Min Act: -0.1700
Data Index: 4405608 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19