Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3282 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1071. Min Range: -3.1071
Max Act: 3.1071. Min Act: -0.1700
Data Index: 6308512 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1071. Min Range: -3.1071
Max Act: 3.0124. Min Act: -0.1700
Data Index: 8735105 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9966. Min Act: -0.1700
Data Index: 862372 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9808. Min Act: -0.1700
Data Index: 2704593 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9966. Min Act: -0.1700
Data Index: 7854765 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9808. Min Act: -0.1700
Data Index: 5502207 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9808. Min Act: -0.1700
Data Index: 8091103 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9808. Min Act: -0.1700
Data Index: 7965238 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9650. Min Act: -0.1700
Data Index: 8112774 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9650. Min Act: -0.1700
Data Index: 1847632 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9650. Min Act: -0.1700
Data Index: 4835398 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9650. Min Act: -0.1700
Data Index: 6479775 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9650. Min Act: -0.1700
Data Index: 6787678 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9491. Min Act: -0.1700
Data Index: 5673215 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9491. Min Act: -0.1700
Data Index: 1014095 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9491. Min Act: -0.1700
Data Index: 2724536 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9491. Min Act: -0.1700
Data Index: 6498811 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9491. Min Act: -0.1700
Data Index: 5724962 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9333. Min Act: -0.1700
Data Index: 6605356 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1071. Min Range: -3.1071
Max Act: 2.9491. Min Act: -0.1700
Data Index: 6746370 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #19