Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1674 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1473. Min Range: -7.1473
Max Act: 7.1473. Min Act: -0.1700
Data Index: 1071845 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.8348. Min Act: -0.1700
Data Index: 454979 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.8348. Min Act: -0.1700
Data Index: 8657906 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.6785. Min Act: -0.1700
Data Index: 4102446 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.6473. Min Act: -0.1700
Data Index: 5912368 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.6160. Min Act: -0.1700
Data Index: 3819541 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.6160. Min Act: -0.1700
Data Index: 7233089 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.5848. Min Act: -0.1700
Data Index: 3951014 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.5535. Min Act: -0.1700
Data Index: 2205262 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.5848. Min Act: -0.1700
Data Index: 6907888 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.5535. Min Act: -0.1700
Data Index: 3592170 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4910. Min Act: -0.1700
Data Index: 2096826 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4910. Min Act: -0.1700
Data Index: 4659217 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4910. Min Act: -0.1700
Data Index: 4118021 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4598. Min Act: -0.1700
Data Index: 106862 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4598. Min Act: -0.1700
Data Index: 2422960 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4598. Min Act: -0.1700
Data Index: 4611958 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4598. Min Act: -0.1700
Data Index: 6268417 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4285. Min Act: -0.1700
Data Index: 6852178 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1473. Min Range: -7.1473
Max Act: 6.4285. Min Act: -0.1700
Data Index: 4726024 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #19