Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5626 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0267. Min Range: -6.0267
Max Act: 6.0267. Min Act: -0.1700
Data Index: 6589118 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.8705. Min Act: -0.1700
Data Index: 7412573 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.8705. Min Act: -0.1700
Data Index: 7795864 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.7767. Min Act: -0.1700
Data Index: 2555750 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.6830. Min Act: -0.1700
Data Index: 4421253 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.6830. Min Act: -0.1700
Data Index: 7678611 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.6830. Min Act: -0.1700
Data Index: 7904106 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.6205. Min Act: -0.1700
Data Index: 1228367 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5892. Min Act: -0.1700
Data Index: 6890994 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5580. Min Act: -0.1700
Data Index: 3241120 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5892. Min Act: -0.1700
Data Index: 6662513 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5580. Min Act: -0.1700
Data Index: 4751044 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5580. Min Act: -0.1700
Data Index: 8802022 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5580. Min Act: -0.1700
Data Index: 5635529 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5580. Min Act: -0.1700
Data Index: 1611253 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5267. Min Act: -0.1700
Data Index: 3052354 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5267. Min Act: -0.1700
Data Index: 6461639 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5267. Min Act: -0.1700
Data Index: 63939 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5267. Min Act: -0.1700
Data Index: 4997656 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0267. Min Range: -6.0267
Max Act: 5.5267. Min Act: -0.1700
Data Index: 1215893 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #19