Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3223 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3939. Min Range: -7.3939
Max Act: 7.3939. Min Act: -0.1700
Data Index: 8574667 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3939. Min Range: -7.3939
Max Act: 7.0502. Min Act: -0.1700
Data Index: 158939 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.9564. Min Act: -0.1700
Data Index: 3078205 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.9252. Min Act: -0.1700
Data Index: 7012458 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.8939. Min Act: -0.1700
Data Index: 2786761 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.8939. Min Act: -0.1700
Data Index: 7086508 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.8627. Min Act: -0.1700
Data Index: 1020312 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.8627. Min Act: -0.1700
Data Index: 7056447 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.8314. Min Act: -0.1700
Data Index: 3328340 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.7689. Min Act: -0.1700
Data Index: 1780017 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.7689. Min Act: -0.1700
Data Index: 909221 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.7377. Min Act: -0.1700
Data Index: 1842063 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.7377. Min Act: -0.1700
Data Index: 6641205 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.7377. Min Act: -0.1700
Data Index: 8138875 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.7377. Min Act: -0.1700
Data Index: 6943468 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.7064. Min Act: -0.1700
Data Index: 1521141 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.6752. Min Act: -0.1700
Data Index: 3591092 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.7064. Min Act: -0.1700
Data Index: 2649006 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.6439. Min Act: -0.1700
Data Index: 5639411 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3939. Min Range: -7.3939
Max Act: 6.6439. Min Act: -0.1700
Data Index: 1949812 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #19