Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 884 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.9876. Min Act: -0.1700
Data Index: 8501761 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.3626. Min Act: -0.1700
Data Index: 6508489 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.3626. Min Act: -0.1700
Data Index: 8320584 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.1751. Min Act: -0.1700
Data Index: 5680575 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.1439. Min Act: -0.1700
Data Index: 5420938 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.1751. Min Act: -0.1700
Data Index: 4908128 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.1439. Min Act: -0.1700
Data Index: 229430 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.1126. Min Act: -0.1700
Data Index: 7661546 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.0813. Min Act: -0.1700
Data Index: 8386959 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.0501. Min Act: -0.1700
Data Index: 7935440 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.0501. Min Act: -0.1700
Data Index: 5964225 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.0501. Min Act: -0.1700
Data Index: 3033024 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9876. Min Range: -4.9876
Max Act: 4.0188. Min Act: -0.1700
Data Index: 8500753 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9876. Min Range: -4.9876
Max Act: 3.9876. Min Act: -0.1700
Data Index: 7101347 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9876. Min Range: -4.9876
Max Act: 3.9876. Min Act: -0.1700
Data Index: 4445089 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9876. Min Range: -4.9876
Max Act: 3.9876. Min Act: -0.1700
Data Index: 2019195 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9876. Min Range: -4.9876
Max Act: 3.9876. Min Act: -0.1700
Data Index: 3748153 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9876. Min Range: -4.9876
Max Act: 3.9876. Min Act: -0.1700
Data Index: 7608775 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9876. Min Range: -4.9876
Max Act: 3.9876. Min Act: -0.1700
Data Index: 6267347 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9876. Min Range: -4.9876
Max Act: 3.9563. Min Act: -0.1700
Data Index: 440595 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #19