Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3639 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.8358. Min Act: -0.1700
Data Index: 6268353 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.8045. Min Act: -0.1700
Data Index: 5719798 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.7733. Min Act: -0.1700
Data Index: 998392 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.8045. Min Act: -0.1700
Data Index: 4546890 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.7733. Min Act: -0.1700
Data Index: 8535233 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.7108. Min Act: -0.1700
Data Index: 2861462 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.6170. Min Act: -0.1700
Data Index: 762367 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.6170. Min Act: -0.1700
Data Index: 7989905 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.5858. Min Act: -0.1700
Data Index: 8751463 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.5858. Min Act: -0.1700
Data Index: 453425 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.5233. Min Act: -0.1700
Data Index: 2286279 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.5233. Min Act: -0.1700
Data Index: 3236977 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.5233. Min Act: -0.1700
Data Index: 8016846 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.5545. Min Act: -0.1700
Data Index: 3952352 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.5233. Min Act: -0.1700
Data Index: 3633176 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.4920. Min Act: -0.1700
Data Index: 2396823 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.4608. Min Act: -0.1700
Data Index: 856369 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.4295. Min Act: -0.1700
Data Index: 7137734 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.4608. Min Act: -0.1700
Data Index: 7760787 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8358. Min Range: -6.8358
Max Act: 6.4608. Min Act: -0.1700
Data Index: 5478157 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #19