Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5383 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0657. Min Range: -5.0657
Max Act: 5.0657. Min Act: -0.1700
Data Index: 1166367 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0657. Min Range: -5.0657
Max Act: 5.0657. Min Act: -0.1700
Data Index: 8595439 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0657. Min Range: -5.0657
Max Act: 5.0344. Min Act: -0.1700
Data Index: 8544611 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.9719. Min Act: -0.1700
Data Index: 256964 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.9719. Min Act: -0.1700
Data Index: 6152108 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.9719. Min Act: -0.1700
Data Index: 8594854 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.9094. Min Act: -0.1700
Data Index: 19071 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8782. Min Act: -0.1700
Data Index: 6152106 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8469. Min Act: -0.1700
Data Index: 3955972 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8469. Min Act: -0.1700
Data Index: 800192 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8469. Min Act: -0.1700
Data Index: 6564720 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8157. Min Act: -0.1700
Data Index: 1540045 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8157. Min Act: -0.1700
Data Index: 5216623 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8157. Min Act: -0.1700
Data Index: 8426421 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8157. Min Act: -0.1700
Data Index: 2224331 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.7844. Min Act: -0.1700
Data Index: 953397 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.7844. Min Act: -0.1700
Data Index: 4886631 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.8157. Min Act: -0.1700
Data Index: 2334423 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.7532. Min Act: -0.1700
Data Index: 1828227 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0657. Min Range: -5.0657
Max Act: 4.7532. Min Act: -0.1700
Data Index: 1506487 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #19