Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4794 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.7216. Min Act: -0.1700
Data Index: 4861120 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.5029. Min Act: -0.1700
Data Index: 4715947 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.3779. Min Act: -0.1700
Data Index: 8702964 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.3466. Min Act: -0.1700
Data Index: 3435936 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.2841. Min Act: -0.1700
Data Index: 603650 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.2216. Min Act: -0.1700
Data Index: 5964874 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.2216. Min Act: -0.1700
Data Index: 3568418 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.2216. Min Act: -0.1700
Data Index: 3351683 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.2216. Min Act: -0.1700
Data Index: 6225116 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.1591. Min Act: -0.1700
Data Index: 4724241 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.1591. Min Act: -0.1700
Data Index: 8829732 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.1591. Min Act: -0.1700
Data Index: 1572003 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.0966. Min Act: -0.1700
Data Index: 4647201 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.1279. Min Act: -0.1700
Data Index: 8701546 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.0654. Min Act: -0.1700
Data Index: 6690626 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.0029. Min Act: -0.1700
Data Index: 3509773 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.0341. Min Act: -0.1700
Data Index: 1727271 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.0341. Min Act: -0.1700
Data Index: 6926779 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.0341. Min Act: -0.1700
Data Index: 8702967 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7216. Min Range: -7.7216
Max Act: 7.0341. Min Act: -0.1700
Data Index: 2423511 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #19