Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1048 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.5625. Min Act: -0.1700
Data Index: 2952716 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.5313. Min Act: -0.1700
Data Index: 3478754 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.4688. Min Act: -0.1700
Data Index: 5159810 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.4375. Min Act: -0.1700
Data Index: 3247318 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.4375. Min Act: -0.1700
Data Index: 4432752 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.4063. Min Act: -0.1700
Data Index: 4772420 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.4063. Min Act: -0.1700
Data Index: 5527389 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.3750. Min Act: -0.1700
Data Index: 6241418 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.3438. Min Act: -0.1700
Data Index: 1016918 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2812. Min Act: -0.1700
Data Index: 8002392 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.3125. Min Act: -0.1700
Data Index: 7225621 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.3125. Min Act: -0.1700
Data Index: 7605557 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2812. Min Act: -0.1700
Data Index: 8053560 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2500. Min Act: -0.1700
Data Index: 7992530 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2187. Min Act: -0.1700
Data Index: 4442523 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2500. Min Act: -0.1700
Data Index: 4332754 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2500. Min Act: -0.1700
Data Index: 3355138 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2500. Min Act: -0.1700
Data Index: 3020259 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2500. Min Act: -0.1700
Data Index: 6058889 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5625. Min Range: -4.5625
Max Act: 4.2500. Min Act: -0.1700
Data Index: 2995886 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #19