Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 393 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.1969. Min Act: -0.1700
Data Index: 3595130 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.1025. Min Act: -0.1700
Data Index: 6694694 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.1025. Min Act: -0.1700
Data Index: 6694705 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.0867. Min Act: -0.1700
Data Index: 754851 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.0551. Min Act: -0.1700
Data Index: 3595128 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.0709. Min Act: -0.1700
Data Index: 6694693 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.0551. Min Act: -0.1700
Data Index: 4783759 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.0078. Min Act: -0.1700
Data Index: 6555873 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.0236. Min Act: -0.1700
Data Index: 6120233 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9920. Min Act: -0.1700
Data Index: 557286 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9920. Min Act: -0.1700
Data Index: 7463042 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9762. Min Act: -0.1700
Data Index: 5491451 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9920. Min Act: -0.1700
Data Index: 6694707 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1969. Min Range: -3.1969
Max Act: 3.0078. Min Act: -0.1700
Data Index: 1548351 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9920. Min Act: -0.1700
Data Index: 6694659 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9762. Min Act: -0.1700
Data Index: 6657451 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9762. Min Act: -0.1700
Data Index: 41069 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9762. Min Act: -0.1700
Data Index: 4737234 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9762. Min Act: -0.1700
Data Index: 3081621 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1969. Min Range: -3.1969
Max Act: 2.9603. Min Act: -0.1700
Data Index: 1039864 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #19