Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4340 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.8125. Min Act: -0.1700
Data Index: 6807287 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.7188. Min Act: -0.1700
Data Index: 168846 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.6563. Min Act: -0.1700
Data Index: 6343696 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.7188. Min Act: -0.1700
Data Index: 1434818 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.6563. Min Act: -0.1700
Data Index: 8798503 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5938. Min Act: -0.1700
Data Index: 4907700 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5625. Min Act: -0.1700
Data Index: 4062728 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5625. Min Act: -0.1700
Data Index: 3432882 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5625. Min Act: -0.1700
Data Index: 807832 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5625. Min Act: -0.1700
Data Index: 7462059 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5625. Min Act: -0.1700
Data Index: 6393069 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5625. Min Act: -0.1700
Data Index: 1900678 (Open Web Text)
Max Activating Token Index: 149
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5313. Min Act: -0.1700
Data Index: 2105710 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5000. Min Act: -0.1700
Data Index: 4235726 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5000. Min Act: -0.1700
Data Index: 6734745 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5000. Min Act: -0.1700
Data Index: 124005 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5000. Min Act: -0.1700
Data Index: 1699790 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.4688. Min Act: -0.1700
Data Index: 5027822 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.5000. Min Act: -0.1700
Data Index: 4938167 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8125. Min Range: -6.8125
Max Act: 6.4688. Min Act: -0.1700
Data Index: 8496639 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #19