Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 62 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0708. Min Range: -5.0708
Max Act: 5.0708. Min Act: -0.1700
Data Index: 8069660 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.9458. Min Act: -0.1700
Data Index: 3397033 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.9145. Min Act: -0.1700
Data Index: 6923308 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.8833. Min Act: -0.1700
Data Index: 4310633 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.8520. Min Act: -0.1700
Data Index: 8543439 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.8208. Min Act: -0.1700
Data Index: 3939438 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.8208. Min Act: -0.1700
Data Index: 7143055 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.8208. Min Act: -0.1700
Data Index: 3387152 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.8208. Min Act: -0.1700
Data Index: 3040781 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7895. Min Act: -0.1700
Data Index: 1249045 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7895. Min Act: -0.1700
Data Index: 6634153 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7895. Min Act: -0.1700
Data Index: 3438237 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7583. Min Act: -0.1700
Data Index: 4152134 (Open Web Text)
Max Activating Token Index: 572
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7583. Min Act: -0.1700
Data Index: 5224051 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7583. Min Act: -0.1700
Data Index: 8465353 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7583. Min Act: -0.1700
Data Index: 5601463 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7270. Min Act: -0.1700
Data Index: 6957312 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7270. Min Act: -0.1700
Data Index: 1342721 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7270. Min Act: -0.1700
Data Index: 7173332 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0708. Min Range: -5.0708
Max Act: 4.7270. Min Act: -0.1700
Data Index: 8045041 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #19