Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2781 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.6011. Min Act: -0.1700
Data Index: 1406279 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.5386. Min Act: -0.1700
Data Index: 6250845 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.5073. Min Act: -0.1700
Data Index: 4287920 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.5073. Min Act: -0.1700
Data Index: 6494862 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.4136. Min Act: -0.1700
Data Index: 3362928 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.4136. Min Act: -0.1700
Data Index: 8141362 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.3823. Min Act: -0.1700
Data Index: 1839550 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.3823. Min Act: -0.1700
Data Index: 4457851 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.3823. Min Act: -0.1700
Data Index: 1808137 (Open Web Text)
Max Activating Token Index: 61
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.3198. Min Act: -0.1700
Data Index: 8624432 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.3198. Min Act: -0.1700
Data Index: 7197902 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.2886. Min Act: -0.1700
Data Index: 4347960 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.2886. Min Act: -0.1700
Data Index: 6088685 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.2261. Min Act: -0.1700
Data Index: 559001 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.1636. Min Act: -0.1700
Data Index: 3474626 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.1636. Min Act: -0.1700
Data Index: 3161071 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.1636. Min Act: -0.1700
Data Index: 6272848 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.1636. Min Act: -0.1700
Data Index: 1414787 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.1636. Min Act: -0.1700
Data Index: 7236813 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6011. Min Range: -5.6011
Max Act: 5.1636. Min Act: -0.1700
Data Index: 3267205 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #19