Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5196. Min Range: -7.5196
Max Act: 7.5196. Min Act: -0.1700
Data Index: 372298 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5196. Min Range: -7.5196
Max Act: 7.1446. Min Act: -0.1700
Data Index: 4562581 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5196. Min Range: -7.5196
Max Act: 7.1134. Min Act: -0.1700
Data Index: 7738529 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5196. Min Range: -7.5196
Max Act: 7.0821. Min Act: -0.1700
Data Index: 6517125 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5196. Min Range: -7.5196
Max Act: 7.0821. Min Act: -0.1700
Data Index: 4110642 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5196. Min Range: -7.5196
Max Act: 7.0196. Min Act: -0.1700
Data Index: 152528 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5196. Min Range: -7.5196
Max Act: 7.0196. Min Act: -0.1700
Data Index: 739101 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.9259. Min Act: -0.1700
Data Index: 6130011 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.8634. Min Act: -0.1700
Data Index: 4780335 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.8634. Min Act: -0.1700
Data Index: 2668968 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.8634. Min Act: -0.1700
Data Index: 1478836 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.7696. Min Act: -0.1700
Data Index: 928977 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.7696. Min Act: -0.1700
Data Index: 284434 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.7384. Min Act: -0.1700
Data Index: 5783867 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5452917 (Open Web Text)
Max Activating Token Index: 117
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5007877 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.7071. Min Act: -0.1700
Data Index: 8566767 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.7071. Min Act: -0.1700
Data Index: 5720701 (Open Web Text)
Max Activating Token Index: 206
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.7071. Min Act: -0.1700
Data Index: 8245390 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5196. Min Range: -7.5196
Max Act: 6.6759. Min Act: -0.1700
Data Index: 55583 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #19