Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2737 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.7246. Min Act: -0.1700
Data Index: 3417375 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.6308. Min Act: -0.1700
Data Index: 7411677 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5683. Min Act: -0.1700
Data Index: 31267 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5683. Min Act: -0.1700
Data Index: 7480539 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5683. Min Act: -0.1700
Data Index: 5385288 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5683. Min Act: -0.1700
Data Index: 7894006 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5683. Min Act: -0.1700
Data Index: 1610491 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5371. Min Act: -0.1700
Data Index: 2683344 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5371. Min Act: -0.1700
Data Index: 7096382 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5058. Min Act: -0.1700
Data Index: 1610490 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5058. Min Act: -0.1700
Data Index: 5385287 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5058. Min Act: -0.1700
Data Index: 5078647 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5058. Min Act: -0.1700
Data Index: 7290980 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.5058. Min Act: -0.1700
Data Index: 7339572 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.4746. Min Act: -0.1700
Data Index: 8731292 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.4746. Min Act: -0.1700
Data Index: 3256190 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.4746. Min Act: -0.1700
Data Index: 114443 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.4433. Min Act: -0.1700
Data Index: 2049060 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.4433. Min Act: -0.1700
Data Index: 4373312 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7246. Min Range: -6.7246
Max Act: 6.4433. Min Act: -0.1700
Data Index: 4644640 (Open Web Text)
Max Activating Token Index: 297
Click toggle to see full text
Truncated
Full Text #19