Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3486 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.7648. Min Act: -0.1700
Data Index: 1649597 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.7648. Min Act: -0.1700
Data Index: 4579099 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.7023. Min Act: -0.1700
Data Index: 442668 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.7023. Min Act: -0.1700
Data Index: 4769268 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.5148. Min Act: -0.1700
Data Index: 7005560 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.5148. Min Act: -0.1700
Data Index: 3175687 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.5148. Min Act: -0.1700
Data Index: 3287282 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.5148. Min Act: -0.1700
Data Index: 6027076 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.4523. Min Act: -0.1700
Data Index: 1908288 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.4523. Min Act: -0.1700
Data Index: 1353605 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.4523. Min Act: -0.1700
Data Index: 4788143 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3898. Min Act: -0.1700
Data Index: 346354 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3898. Min Act: -0.1700
Data Index: 5535078 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3273. Min Act: -0.1700
Data Index: 2987336 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3273. Min Act: -0.1700
Data Index: 4061658 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3898. Min Act: -0.1700
Data Index: 3619456 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3273. Min Act: -0.1700
Data Index: 2031066 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3273. Min Act: -0.1700
Data Index: 4555653 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3898. Min Act: -0.1700
Data Index: 5277866 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.7648. Min Range: -9.7648
Max Act: 9.3273. Min Act: -0.1700
Data Index: 3175686 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #19