Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 893 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.3203. Min Act: -0.1700
Data Index: 8240764 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.2890. Min Act: -0.1700
Data Index: 2006860 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.1953. Min Act: -0.1700
Data Index: 2119974 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.1015. Min Act: -0.1700
Data Index: 7696137 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.0702. Min Act: -0.1700
Data Index: 3586474 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.0702. Min Act: -0.1700
Data Index: 1581782 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.0390. Min Act: -0.1700
Data Index: 978219 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.0077. Min Act: -0.1700
Data Index: 2196325 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.3203. Min Range: -4.3203
Max Act: 4.0077. Min Act: -0.1700
Data Index: 3925334 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.9452. Min Act: -0.1700
Data Index: 2962347 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.9452. Min Act: -0.1700
Data Index: 6716732 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.9452. Min Act: -0.1700
Data Index: 8493319 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.9139. Min Act: -0.1700
Data Index: 390186 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.9139. Min Act: -0.1700
Data Index: 5001300 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.9139. Min Act: -0.1700
Data Index: 2706942 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.9139. Min Act: -0.1700
Data Index: 3467850 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.9452. Min Act: -0.1700
Data Index: 6708057 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.8827. Min Act: -0.1700
Data Index: 754096 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.8827. Min Act: -0.1700
Data Index: 7825245 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.3203. Min Range: -4.3203
Max Act: 3.8827. Min Act: -0.1700
Data Index: 3998344 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #19