Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2145 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.1285. Min Range: -7.1285
Max Act: 7.1285. Min Act: -0.1700
Data Index: 599250 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1285. Min Range: -7.1285
Max Act: 7.0660. Min Act: -0.1700
Data Index: 1403842 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1285. Min Range: -7.1285
Max Act: 7.0348. Min Act: -0.1700
Data Index: 897609 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1285. Min Range: -7.1285
Max Act: 7.0035. Min Act: -0.1700
Data Index: 793253 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.9098. Min Act: -0.1700
Data Index: 2899823 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.7848. Min Act: -0.1700
Data Index: 8038156 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.8160. Min Act: -0.1700
Data Index: 7458385 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.8160. Min Act: -0.1700
Data Index: 7589682 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.7848. Min Act: -0.1700
Data Index: 5756444 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.7535. Min Act: -0.1699
Data Index: 4825122 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.7535. Min Act: -0.1700
Data Index: 7332902 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.7535. Min Act: -0.1700
Data Index: 6500798 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.7535. Min Act: -0.1700
Data Index: 1399109 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.7535. Min Act: -0.1700
Data Index: 1403853 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.7535. Min Act: -0.1700
Data Index: 897608 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.6910. Min Act: -0.1700
Data Index: 2882048 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.6598. Min Act: -0.1700
Data Index: 7400173 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.6598. Min Act: -0.1700
Data Index: 7589681 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.6598. Min Act: -0.1700
Data Index: 2424237 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1285. Min Range: -7.1285
Max Act: 6.6910. Min Act: -0.1700
Data Index: 2989252 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19