Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer
Dataset: Open Web Text
Neuron 533 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-small')
Text #0
Max Range: 6.1292. Min Range: -6.1292
Max Act: 6.1292. Min Act: -0.1700
Data Index: 1587266 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1292. Min Range: -6.1292
Max Act: 6.1292. Min Act: -0.1700
Data Index: 8395674 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1292. Min Range: -6.1292
Max Act: 6.0667. Min Act: -0.1700
Data Index: 2867399 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1292. Min Range: -6.1292
Max Act: 6.0980. Min Act: -0.1700
Data Index: 6436059 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1292. Min Range: -6.1292
Max Act: 6.0355. Min Act: -0.1700
Data Index: 6336515 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1292. Min Range: -6.1292
Max Act: 6.0667. Min Act: -0.1700
Data Index: 5489840 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1292. Min Range: -6.1292
Max Act: 6.0042. Min Act: -0.1700
Data Index: 1713501 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.9417. Min Act: -0.1700
Data Index: 8660922 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.9417. Min Act: -0.1700
Data Index: 17959 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.9417. Min Act: -0.1700
Data Index: 3642557 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8792. Min Act: -0.1700
Data Index: 3495874 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.9105. Min Act: -0.1700
Data Index: 2348045 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8792. Min Act: -0.1700
Data Index: 5146329 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8792. Min Act: -0.1700
Data Index: 7110185 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8792. Min Act: -0.1700
Data Index: 3082211 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8792. Min Act: -0.1700
Data Index: 1458024 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8480. Min Act: -0.1700
Data Index: 231060 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8167. Min Act: -0.1700
Data Index: 3622676 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8167. Min Act: -0.1700
Data Index: 466879 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1292. Min Range: -6.1292
Max Act: 5.8480. Min Act: -0.1700
Data Index: 2271629 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #19