Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3052 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.2145. Min Act: -0.1700
Data Index: 7398559 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1832. Min Act: -0.1700
Data Index: 884524 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1520. Min Act: -0.1700
Data Index: 382773 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1520. Min Act: -0.1700
Data Index: 4947944 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1520. Min Act: -0.1700
Data Index: 829612 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1520. Min Act: -0.1700
Data Index: 6549746 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1520. Min Act: -0.1700
Data Index: 7763724 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1520. Min Act: -0.1700
Data Index: 2389090 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1520. Min Act: -0.1700
Data Index: 3339520 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1520. Min Act: -0.1700
Data Index: 7915304 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1207. Min Act: -0.1700
Data Index: 715574 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1207. Min Act: -0.1700
Data Index: 3728023 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.0895. Min Act: -0.1700
Data Index: 1696243 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1207. Min Act: -0.1700
Data Index: 2502500 (Open Web Text)
Max Activating Token Index: 180
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.1207. Min Act: -0.1700
Data Index: 4903577 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.0895. Min Act: -0.1700
Data Index: 7944866 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.0895. Min Act: -0.1700
Data Index: 8238730 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.0895. Min Act: -0.1700
Data Index: 2375793 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.0895. Min Act: -0.1700
Data Index: 5753096 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2145. Min Range: -5.2145
Max Act: 5.0895. Min Act: -0.1700
Data Index: 5188662 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #19