Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2471 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.9635. Min Act: -0.1700
Data Index: 6501421 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.9010. Min Act: -0.1700
Data Index: 3592258 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.8073. Min Act: -0.1700
Data Index: 1294926 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.8073. Min Act: -0.1700
Data Index: 2477212 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.7448. Min Act: -0.1700
Data Index: 7650144 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.7135. Min Act: -0.1700
Data Index: 6442564 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.7135. Min Act: -0.1700
Data Index: 3702260 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.6823. Min Act: -0.1700
Data Index: 51532 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.6510. Min Act: -0.1700
Data Index: 484444 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.6198. Min Act: -0.1700
Data Index: 8063477 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.6198. Min Act: -0.1700
Data Index: 1965012 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.6198. Min Act: -0.1700
Data Index: 7937907 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.5885. Min Act: -0.1700
Data Index: 4695125 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.5885. Min Act: -0.1700
Data Index: 259725 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.5885. Min Act: -0.1700
Data Index: 7432584 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.5885. Min Act: -0.1700
Data Index: 2373118 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.5573. Min Act: -0.1700
Data Index: 5501481 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.5573. Min Act: -0.1700
Data Index: 8785080 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.5573. Min Act: -0.1700
Data Index: 6505151 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9635. Min Range: -5.9635
Max Act: 5.5260. Min Act: -0.1700
Data Index: 689772 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #19