Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3443 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 12.0162. Min Range: -12.0162
Max Act: 12.0162. Min Act: -0.1700
Data Index: 6116151 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.8912. Min Act: -0.1700
Data Index: 1483687 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.7037. Min Act: -0.1700
Data Index: 7883469 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.6412. Min Act: -0.1700
Data Index: 76659 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.5162. Min Act: -0.1700
Data Index: 1291782 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.5162. Min Act: -0.1700
Data Index: 2831725 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.3912. Min Act: -0.1700
Data Index: 1231247 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.3912. Min Act: -0.1700
Data Index: 3424855 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.2662. Min Act: -0.1700
Data Index: 2683792 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.2037. Min Act: -0.1700
Data Index: 1118831 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.2037. Min Act: -0.1700
Data Index: 5545819 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.1412. Min Act: -0.1700
Data Index: 6044993 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.2037. Min Act: -0.1700
Data Index: 8031339 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.1412. Min Act: -0.1700
Data Index: 794887 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.1412. Min Act: -0.1700
Data Index: 7753182 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.2037. Min Act: -0.1700
Data Index: 4281288 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.1412. Min Act: -0.1700
Data Index: 8750732 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.2037. Min Act: -0.1700
Data Index: 3610815 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.1412. Min Act: -0.1700
Data Index: 6454730 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 12.0162. Min Range: -12.0162
Max Act: 11.0787. Min Act: -0.1700
Data Index: 2387958 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #19