Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5046 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5314. Min Range: -7.5314
Max Act: 7.5314. Min Act: -0.1700
Data Index: 6757466 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5314. Min Range: -7.5314
Max Act: 7.2814. Min Act: -0.1700
Data Index: 2650772 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5314. Min Range: -7.5314
Max Act: 7.1877. Min Act: -0.1700
Data Index: 5113284 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.9689. Min Act: -0.1700
Data Index: 2476115 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.9377. Min Act: -0.1700
Data Index: 7889941 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.7814. Min Act: -0.1700
Data Index: 2572246 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.7814. Min Act: -0.1700
Data Index: 2552469 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.7814. Min Act: -0.1700
Data Index: 3522920 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.8127. Min Act: -0.1700
Data Index: 732714 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.7502. Min Act: -0.1700
Data Index: 2315703 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.7502. Min Act: -0.1700
Data Index: 999407 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.7502. Min Act: -0.1700
Data Index: 4724015 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.6877. Min Act: -0.1700
Data Index: 4516288 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.6877. Min Act: -0.1700
Data Index: 5433806 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.6564. Min Act: -0.1700
Data Index: 2168529 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.6564. Min Act: -0.1700
Data Index: 6366169 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.6252. Min Act: -0.1700
Data Index: 5664629 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.5939. Min Act: -0.1698
Data Index: 1596037 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.6564. Min Act: -0.1700
Data Index: 1505102 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5314. Min Range: -7.5314
Max Act: 6.6564. Min Act: -0.1700
Data Index: 4910281 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19