Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2740 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.2914. Min Act: -0.1700
Data Index: 3063899 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.2443. Min Act: -0.1700
Data Index: 7719853 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.1499. Min Act: -0.1700
Data Index: 2181643 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.1027. Min Act: -0.1700
Data Index: 3644910 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.1342. Min Act: -0.1700
Data Index: 2612750 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.0869. Min Act: -0.1700
Data Index: 4033369 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.0712. Min Act: -0.1700
Data Index: 6303175 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.0712. Min Act: -0.1700
Data Index: 1894787 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.0554. Min Act: -0.1700
Data Index: 8468914 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.0396. Min Act: -0.1700
Data Index: 3730308 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.0238. Min Act: -0.1700
Data Index: 1439302 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.2914. Min Range: -3.2914
Max Act: 2.9922. Min Act: -0.1700
Data Index: 7664072 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.2914. Min Range: -3.2914
Max Act: 2.9764. Min Act: -0.1700
Data Index: 3652740 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.2914. Min Range: -3.2914
Max Act: 3.0080. Min Act: -0.1700
Data Index: 7691435 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.2914. Min Range: -3.2914
Max Act: 2.9922. Min Act: -0.1700
Data Index: 2248786 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.2914. Min Range: -3.2914
Max Act: 2.9764. Min Act: -0.1700
Data Index: 2980663 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.2914. Min Range: -3.2914
Max Act: 2.9447. Min Act: -0.1700
Data Index: 1526924 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.2914. Min Range: -3.2914
Max Act: 2.9764. Min Act: -0.1700
Data Index: 3221490 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.2914. Min Range: -3.2914
Max Act: 2.9606. Min Act: -0.1700
Data Index: 5490607 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.2914. Min Range: -3.2914
Max Act: 2.9447. Min Act: -0.1700
Data Index: 4752287 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #19