Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3991 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.9453. Min Act: -0.1700
Data Index: 5186142 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.8828. Min Act: -0.1700
Data Index: 6865202 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.3828. Min Act: -0.1700
Data Index: 8598515 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.3828. Min Act: -0.1700
Data Index: 5324179 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.3515. Min Act: -0.1700
Data Index: 3297677 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.3515. Min Act: -0.1700
Data Index: 930309 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.2578. Min Act: -0.1700
Data Index: 7215286 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.2578. Min Act: -0.1700
Data Index: 806229 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.2265. Min Act: -0.1700
Data Index: 4781050 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.2265. Min Act: -0.1700
Data Index: 1899327 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.2265. Min Act: -0.1700
Data Index: 6014128 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.1953. Min Act: -0.1700
Data Index: 1651582 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.1015. Min Act: -0.1700
Data Index: 7085025 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.1015. Min Act: -0.1700
Data Index: 7303283 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.0390. Min Act: -0.1700
Data Index: 8781945 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.0703. Min Act: -0.1700
Data Index: 6946798 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.0703. Min Act: -0.1700
Data Index: 6558302 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.0390. Min Act: -0.1700
Data Index: 5580065 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.0078. Min Act: -0.1700
Data Index: 5710566 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9453. Min Range: -7.9453
Max Act: 7.0390. Min Act: -0.1700
Data Index: 2539936 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #19