Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4623 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.5057. Min Act: -0.1700
Data Index: 3660687 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.5057. Min Act: -0.1700
Data Index: 6988240 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.4900. Min Act: -0.1700
Data Index: 5690000 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.4744. Min Act: -0.1700
Data Index: 5080271 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.4430. Min Act: -0.1700
Data Index: 1690236 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.4430. Min Act: -0.1700
Data Index: 4062746 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.4430. Min Act: -0.1700
Data Index: 1066303 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.4274. Min Act: -0.1700
Data Index: 5741013 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.4274. Min Act: -0.1700
Data Index: 7426631 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.4274. Min Act: -0.1700
Data Index: 7198621 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3960. Min Act: -0.1700
Data Index: 8784386 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3646. Min Act: -0.1700
Data Index: 7518630 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3490. Min Act: -0.1700
Data Index: 6435671 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3646. Min Act: -0.1700
Data Index: 7497393 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3333. Min Act: -0.1700
Data Index: 6367769 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3333. Min Act: -0.1700
Data Index: 3146656 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3333. Min Act: -0.1700
Data Index: 6226688 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3333. Min Act: -0.1700
Data Index: 5384113 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3333. Min Act: -0.1700
Data Index: 3459981 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5057. Min Range: -3.5057
Max Act: 3.3333. Min Act: -0.1700
Data Index: 5484163 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #19