Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2159 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.7745. Min Act: -0.1700
Data Index: 6360091 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.7432. Min Act: -0.1700
Data Index: 3824190 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.7432. Min Act: -0.1700
Data Index: 2840546 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.7745. Min Act: -0.1700
Data Index: 8320680 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.7120. Min Act: -0.1700
Data Index: 5106157 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.7120. Min Act: -0.1700
Data Index: 8417960 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.7120. Min Act: -0.1700
Data Index: 3258580 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.6495. Min Act: -0.1700
Data Index: 2987725 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.6495. Min Act: -0.1700
Data Index: 6512391 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.6495. Min Act: -0.1700
Data Index: 650775 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.6495. Min Act: -0.1700
Data Index: 5257822 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.6182. Min Act: -0.1700
Data Index: 650757 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.5870. Min Act: -0.1700
Data Index: 2163487 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.5870. Min Act: -0.1700
Data Index: 1049862 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.5557. Min Act: -0.1700
Data Index: 8192021 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.5870. Min Act: -0.1700
Data Index: 60906 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.5870. Min Act: -0.1700
Data Index: 7938051 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.5557. Min Act: -0.1700
Data Index: 6095343 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.5557. Min Act: -0.1700
Data Index: 3258588 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7745. Min Range: -5.7745
Max Act: 5.5557. Min Act: -0.1700
Data Index: 3358676 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #19