Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 418 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.9529. Min Act: -0.1700
Data Index: 1601054 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.9529. Min Act: -0.1700
Data Index: 1188480 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.9529. Min Act: -0.1700
Data Index: 139049 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.8904. Min Act: -0.1700
Data Index: 3867806 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.8904. Min Act: -0.1700
Data Index: 6556121 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.9529. Min Act: -0.1700
Data Index: 6156920 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.8904. Min Act: -0.1700
Data Index: 8510234 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.8904. Min Act: -0.1700
Data Index: 7082592 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.7654. Min Act: -0.1700
Data Index: 7583237 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.7654. Min Act: -0.1700
Data Index: 6471956 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.7029. Min Act: -0.1700
Data Index: 3915847 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.6091. Min Act: -0.1700
Data Index: 3517900 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.6091. Min Act: -0.1700
Data Index: 7167369 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.6091. Min Act: -0.1700
Data Index: 8181866 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.5779. Min Act: -0.1700
Data Index: 8749678 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.5779. Min Act: -0.1700
Data Index: 3393608 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.4841. Min Act: -0.1700
Data Index: 8061233 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.4841. Min Act: -0.1700
Data Index: 6158948 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.4841. Min Act: -0.1700
Data Index: 8064154 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.9529. Min Range: -7.9529
Max Act: 7.4529. Min Act: -0.1700
Data Index: 1250766 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #19