Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3021 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.7139. Min Act: -0.1700
Data Index: 3554627 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.5264. Min Act: -0.1700
Data Index: 535675 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.4327. Min Act: -0.1700
Data Index: 3329096 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.3389. Min Act: -0.1700
Data Index: 3941227 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.3077. Min Act: -0.1700
Data Index: 1210574 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.3389. Min Act: -0.1700
Data Index: 7080870 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.2764. Min Act: -0.1700
Data Index: 6856699 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.2452. Min Act: -0.1700
Data Index: 4678993 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.2452. Min Act: -0.1700
Data Index: 1320638 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.2139. Min Act: -0.1700
Data Index: 4652370 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1514. Min Act: -0.1700
Data Index: 7279722 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1514. Min Act: -0.1700
Data Index: 3662523 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1514. Min Act: -0.1700
Data Index: 3526094 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1514. Min Act: -0.1700
Data Index: 6310638 (Open Web Text)
Max Activating Token Index: 672
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1514. Min Act: -0.1700
Data Index: 2387488 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1514. Min Act: -0.1700
Data Index: 3668123 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1202. Min Act: -0.1700
Data Index: 5988648 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1202. Min Act: -0.1700
Data Index: 124156 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1202. Min Act: -0.1700
Data Index: 6884851 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7139. Min Range: -6.7139
Max Act: 6.1202. Min Act: -0.1700
Data Index: 619766 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #19