Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2956 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.7080. Min Act: -0.1700
Data Index: 1078256 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.5830. Min Act: -0.1700
Data Index: 8011338 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.5830. Min Act: -0.1700
Data Index: 3935748 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.5518. Min Act: -0.1700
Data Index: 3688201 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.5205. Min Act: -0.1700
Data Index: 364349 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.5518. Min Act: -0.1700
Data Index: 4188381 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4893. Min Act: -0.1700
Data Index: 3045526 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4893. Min Act: -0.1700
Data Index: 7635480 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4893. Min Act: -0.1700
Data Index: 6429794 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4580. Min Act: -0.1700
Data Index: 4522029 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4580. Min Act: -0.1700
Data Index: 2255505 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4580. Min Act: -0.1700
Data Index: 552603 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.4268. Min Act: -0.1700
Data Index: 32500 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3955. Min Act: -0.1700
Data Index: 3731235 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3955. Min Act: -0.1700
Data Index: 3899683 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3955. Min Act: -0.1700
Data Index: 5419585 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3955. Min Act: -0.1700
Data Index: 1208202 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3643. Min Act: -0.1700
Data Index: 6312555 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3643. Min Act: -0.1700
Data Index: 7465058 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7080. Min Range: -5.7080
Max Act: 5.3643. Min Act: -0.1700
Data Index: 41723 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19