Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5564 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1724. Min Range: -5.1724
Max Act: 5.1724. Min Act: -0.1700
Data Index: 5556008 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1724. Min Range: -5.1724
Max Act: 5.1724. Min Act: -0.1700
Data Index: 5556011 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1724. Min Range: -5.1724
Max Act: 5.0787. Min Act: -0.1700
Data Index: 5556010 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1724. Min Range: -5.1724
Max Act: 5.0474. Min Act: -0.1700
Data Index: 5556012 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1724. Min Range: -5.1724
Max Act: 5.0162. Min Act: -0.1700
Data Index: 5556009 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.9537. Min Act: -0.1700
Data Index: 5556013 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.7662. Min Act: -0.1700
Data Index: 5556007 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.7974. Min Act: -0.1700
Data Index: 8661190 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.7662. Min Act: -0.1700
Data Index: 5055824 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.7349. Min Act: -0.1700
Data Index: 7062455 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.7349. Min Act: -0.1700
Data Index: 789926 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.6724. Min Act: -0.1700
Data Index: 4165393 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.6724. Min Act: -0.1700
Data Index: 5556014 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.6099. Min Act: -0.1700
Data Index: 3348479 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.5787. Min Act: -0.1700
Data Index: 7913796 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.5474. Min Act: -0.1700
Data Index: 8182802 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.5787. Min Act: -0.1700
Data Index: 3110290 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.5787. Min Act: -0.1700
Data Index: 2142182 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.5474. Min Act: -0.1700
Data Index: 4165392 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1724. Min Range: -5.1724
Max Act: 4.5474. Min Act: -0.1700
Data Index: 1696118 (Open Web Text)
Max Activating Token Index: 36
Click toggle to see full text
Truncated
Full Text #19