Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1533 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.9199. Min Act: -0.1700
Data Index: 966332 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.8261. Min Act: -0.1700
Data Index: 1775992 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7948. Min Act: -0.1700
Data Index: 3886683 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7948. Min Act: -0.1700
Data Index: 777548 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7948. Min Act: -0.1700
Data Index: 5551185 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7635. Min Act: -0.1700
Data Index: 5616916 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7009. Min Act: -0.1700
Data Index: 2931591 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7009. Min Act: -0.1700
Data Index: 4883097 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7009. Min Act: -0.1700
Data Index: 1677386 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7009. Min Act: -0.1700
Data Index: 6160733 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.7009. Min Act: -0.1700
Data Index: 7472965 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6697. Min Act: -0.1700
Data Index: 819599 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6697. Min Act: -0.1700
Data Index: 3165900 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6697. Min Act: -0.1700
Data Index: 6843454 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6697. Min Act: -0.1700
Data Index: 3275931 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6697. Min Act: -0.1700
Data Index: 1187894 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6697. Min Act: -0.1700
Data Index: 5403843 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6384. Min Act: -0.1700
Data Index: 2618035 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6384. Min Act: -0.1700
Data Index: 1485670 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9199. Min Range: -3.9199
Max Act: 3.6384. Min Act: -0.1700
Data Index: 5166679 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19