Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4899 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0876. Min Range: -6.0876
Max Act: 6.0876. Min Act: -0.1700
Data Index: 8279401 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0876. Min Range: -6.0876
Max Act: 6.0564. Min Act: -0.1700
Data Index: 2450026 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8689. Min Act: -0.1700
Data Index: 2450027 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8376. Min Act: -0.1700
Data Index: 2905568 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 8805150 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.8064. Min Act: -0.1700
Data Index: 2383237 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.7439. Min Act: -0.1700
Data Index: 5059036 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.6189. Min Act: -0.1700
Data Index: 5617501 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.5564. Min Act: -0.1700
Data Index: 7236390 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.4626. Min Act: -0.1700
Data Index: 4993404 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.3064. Min Act: -0.1700
Data Index: 3536401 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.2439. Min Act: -0.1700
Data Index: 1542029 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.2126. Min Act: -0.1700
Data Index: 4450367 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.1814. Min Act: -0.1700
Data Index: 6974704 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.1501. Min Act: -0.1700
Data Index: 7222901 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.1189. Min Act: -0.1700
Data Index: 5617502 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.1189. Min Act: -0.1700
Data Index: 2954264 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.1189. Min Act: -0.1700
Data Index: 5983275 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.1189. Min Act: -0.1700
Data Index: 7567781 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0876. Min Range: -6.0876
Max Act: 5.1189. Min Act: -0.1700
Data Index: 2737218 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #19