Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3129 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.9102. Min Act: -0.1700
Data Index: 6001043 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.7852. Min Act: -0.1700
Data Index: 3897628 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.6602. Min Act: -0.1700
Data Index: 7763781 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.6290. Min Act: -0.1700
Data Index: 2993751 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.6290. Min Act: -0.1700
Data Index: 5487707 (Open Web Text)
Max Activating Token Index: 971
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4727. Min Act: -0.1700
Data Index: 5872058 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4727. Min Act: -0.1700
Data Index: 5023883 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4415. Min Act: -0.1700
Data Index: 540213 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4102. Min Act: -0.1700
Data Index: 4098374 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.4102. Min Act: -0.1700
Data Index: 6400260 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.3790. Min Act: -0.1700
Data Index: 5225628 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.3477. Min Act: -0.1700
Data Index: 569511 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.3790. Min Act: -0.1700
Data Index: 3711000 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2540. Min Act: -0.1700
Data Index: 513514 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2852. Min Act: -0.1700
Data Index: 1648098 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.3165. Min Act: -0.1700
Data Index: 8189815 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2540. Min Act: -0.1700
Data Index: 4837414 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.2227. Min Act: -0.1700
Data Index: 3897627 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.1915. Min Act: -0.1700
Data Index: 3761468 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9102. Min Range: -6.9102
Max Act: 6.1915. Min Act: -0.1700
Data Index: 3918468 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #19