Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 264 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.7572. Min Act: -0.1700
Data Index: 90668 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 4497080 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.7259. Min Act: -0.1700
Data Index: 8443291 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.7259. Min Act: -0.1700
Data Index: 3511366 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.7259. Min Act: -0.1700
Data Index: 6908691 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 3618678 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.7259. Min Act: -0.1700
Data Index: 4069182 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 5647472 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 5708261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 2740776 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 5327017 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 53936 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 3233575 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 167193 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 3575891 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6946. Min Act: -0.1700
Data Index: 1840713 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6634. Min Act: -0.1700
Data Index: 7135890 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6634. Min Act: -0.1700
Data Index: 4619951 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6634. Min Act: -0.1700
Data Index: 5209085 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7572. Min Range: -3.7572
Max Act: 3.6634. Min Act: -0.1700
Data Index: 4015637 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19