Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5584 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0136. Min Range: -5.0136
Max Act: 5.0136. Min Act: -0.1700
Data Index: 1561558 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0136. Min Range: -5.0136
Max Act: 5.0136. Min Act: -0.1700
Data Index: 2725404 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9824. Min Act: -0.1700
Data Index: 4449306 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9511. Min Act: -0.1700
Data Index: 7283158 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9511. Min Act: -0.1700
Data Index: 3937296 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9511. Min Act: -0.1700
Data Index: 5764036 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9511. Min Act: -0.1700
Data Index: 8680555 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9199. Min Act: -0.1700
Data Index: 2499549 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9511. Min Act: -0.1700
Data Index: 7142052 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9199. Min Act: -0.1700
Data Index: 3154357 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9199. Min Act: -0.1699
Data Index: 1288549 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9199. Min Act: -0.1700
Data Index: 8720432 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9199. Min Act: -0.1700
Data Index: 8701016 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9199. Min Act: -0.1700
Data Index: 1664474 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9199. Min Act: -0.1700
Data Index: 5309608 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.9199. Min Act: -0.1700
Data Index: 7930120 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.8886. Min Act: -0.1700
Data Index: 8022373 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.8886. Min Act: -0.1700
Data Index: 980788 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.8574. Min Act: -0.1700
Data Index: 2499548 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0136. Min Range: -5.0136
Max Act: 4.8886. Min Act: -0.1700
Data Index: 6839671 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #19