Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2883 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.7680. Min Act: -0.1700
Data Index: 1714256 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.6430. Min Act: -0.1700
Data Index: 798386 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.6430. Min Act: -0.1700
Data Index: 1028283 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.6430. Min Act: -0.1700
Data Index: 6336680 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.6117. Min Act: -0.1700
Data Index: 2037015 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.6117. Min Act: -0.1700
Data Index: 1111174 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.6117. Min Act: -0.1700
Data Index: 2334236 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.6117. Min Act: -0.1700
Data Index: 1481629 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5805. Min Act: -0.1700
Data Index: 2648381 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5805. Min Act: -0.1700
Data Index: 1049938 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5805. Min Act: -0.1700
Data Index: 5604937 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5180. Min Act: -0.1700
Data Index: 5856873 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5492. Min Act: -0.1700
Data Index: 5686113 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5492. Min Act: -0.1700
Data Index: 5361337 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5492. Min Act: -0.1700
Data Index: 2403819 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5492. Min Act: -0.1700
Data Index: 4886592 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5492. Min Act: -0.1700
Data Index: 4816042 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5492. Min Act: -0.1700
Data Index: 3701934 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5492. Min Act: -0.1700
Data Index: 3404660 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7680. Min Range: -5.7680
Max Act: 5.5492. Min Act: -0.1700
Data Index: 360615 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #19