Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2596 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1747. Min Range: -4.1747
Max Act: 4.1747. Min Act: -0.1700
Data Index: 39480 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1747. Min Range: -4.1747
Max Act: 4.0809. Min Act: -0.1700
Data Index: 7712408 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1747. Min Range: -4.1747
Max Act: 4.0497. Min Act: -0.1700
Data Index: 5519244 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1747. Min Range: -4.1747
Max Act: 4.0497. Min Act: -0.1700
Data Index: 7089633 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1747. Min Range: -4.1747
Max Act: 4.0184. Min Act: -0.1700
Data Index: 4618128 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1747. Min Range: -4.1747
Max Act: 4.0497. Min Act: -0.1700
Data Index: 6848381 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1747. Min Range: -4.1747
Max Act: 4.0497. Min Act: -0.1700
Data Index: 7903617 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1747. Min Range: -4.1747
Max Act: 4.0184. Min Act: -0.1700
Data Index: 3895063 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.9872. Min Act: -0.1700
Data Index: 1674686 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.9872. Min Act: -0.1700
Data Index: 3556657 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.9872. Min Act: -0.1700
Data Index: 61166 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.9559. Min Act: -0.1700
Data Index: 804442 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.9559. Min Act: -0.1700
Data Index: 8507416 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.9246. Min Act: -0.1700
Data Index: 269459 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.8934. Min Act: -0.1700
Data Index: 4840811 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.8934. Min Act: -0.1700
Data Index: 1629547 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.8934. Min Act: -0.1700
Data Index: 1355917 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.8934. Min Act: -0.1700
Data Index: 1916468 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.8934. Min Act: -0.1700
Data Index: 6165104 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1747. Min Range: -4.1747
Max Act: 3.8934. Min Act: -0.1700
Data Index: 2670557 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #19