Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5932 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0511. Min Range: -6.0511
Max Act: 6.0511. Min Act: -0.1700
Data Index: 17091 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.8636. Min Act: -0.1700
Data Index: 4581187 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.8011. Min Act: -0.1700
Data Index: 2944478 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.8636. Min Act: -0.1700
Data Index: 120223 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.8011. Min Act: -0.1700
Data Index: 8058470 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.8011. Min Act: -0.1700
Data Index: 3063155 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.8011. Min Act: -0.1700
Data Index: 8636846 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.8011. Min Act: -0.1700
Data Index: 7371855 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.7698. Min Act: -0.1700
Data Index: 3431663 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.7386. Min Act: -0.1700
Data Index: 2412352 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.7386. Min Act: -0.1700
Data Index: 5155676 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.7386. Min Act: -0.1700
Data Index: 4787914 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.7073. Min Act: -0.1700
Data Index: 2319613 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.7073. Min Act: -0.1700
Data Index: 1961845 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6761. Min Act: -0.1700
Data Index: 5229857 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6761. Min Act: -0.1700
Data Index: 1522854 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6448. Min Act: -0.1700
Data Index: 5034681 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6448. Min Act: -0.1700
Data Index: 1521830 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6136. Min Act: -0.1700
Data Index: 6079440 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0511. Min Range: -6.0511
Max Act: 5.6448. Min Act: -0.1700
Data Index: 1126118 (Open Web Text)
Max Activating Token Index: 246
Click toggle to see full text
Truncated
Full Text #19