Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2460 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1146. Min Range: -5.1146
Max Act: 5.1146. Min Act: -0.1700
Data Index: 1949497 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1146. Min Range: -5.1146
Max Act: 5.0521. Min Act: -0.1700
Data Index: 5771071 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.9271. Min Act: -0.1700
Data Index: 2377946 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.9271. Min Act: -0.1700
Data Index: 6255812 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.9271. Min Act: -0.1700
Data Index: 1954124 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.8958. Min Act: -0.1700
Data Index: 827228 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.8958. Min Act: -0.1700
Data Index: 5074755 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.8646. Min Act: -0.1700
Data Index: 5889799 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.8333. Min Act: -0.1700
Data Index: 5187515 (Open Web Text)
Max Activating Token Index: 947
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.8021. Min Act: -0.1700
Data Index: 2151927 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.8021. Min Act: -0.1700
Data Index: 8369301 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.7708. Min Act: -0.1700
Data Index: 5702343 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.7396. Min Act: -0.1700
Data Index: 3763987 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.7396. Min Act: -0.1700
Data Index: 5941061 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.6771. Min Act: -0.1700
Data Index: 4442010 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.7083. Min Act: -0.1700
Data Index: 6803562 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.6771. Min Act: -0.1700
Data Index: 4924679 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.6771. Min Act: -0.1700
Data Index: 1391908 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.6771. Min Act: -0.1700
Data Index: 6282169 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1146. Min Range: -5.1146
Max Act: 4.6771. Min Act: -0.1700
Data Index: 7783307 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #19