Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2978 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.1099. Min Act: -0.1700
Data Index: 703610 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.0474. Min Act: -0.1700
Data Index: 1145362 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.0474. Min Act: -0.1700
Data Index: 6248895 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.0474. Min Act: -0.1700
Data Index: 3895702 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.0474. Min Act: -0.1700
Data Index: 134785 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.0474. Min Act: -0.1700
Data Index: 2148868 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.0161. Min Act: -0.1700
Data Index: 3189828 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9849. Min Act: -0.1700
Data Index: 6932961 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1099. Min Range: -5.1099
Max Act: 5.0161. Min Act: -0.1700
Data Index: 653876 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9849. Min Act: -0.1700
Data Index: 324599 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9849. Min Act: -0.1700
Data Index: 1833311 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9536. Min Act: -0.1700
Data Index: 6812601 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9536. Min Act: -0.1700
Data Index: 8351735 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 6950523 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9536. Min Act: -0.1700
Data Index: 4276182 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 2997941 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 4892860 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 5024034 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 3941362 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1099. Min Range: -5.1099
Max Act: 4.9224. Min Act: -0.1700
Data Index: 6057628 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #19