Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 447 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.6648. Min Act: -0.1700
Data Index: 5772378 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.6336. Min Act: -0.1700
Data Index: 6390475 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.6023. Min Act: -0.1700
Data Index: 7829198 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.5711. Min Act: -0.1700
Data Index: 2013612 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.5711. Min Act: -0.1700
Data Index: 6468207 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.5398. Min Act: -0.1700
Data Index: 425731 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.5086. Min Act: -0.1700
Data Index: 614909 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.5086. Min Act: -0.1700
Data Index: 425732 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.5086. Min Act: -0.1700
Data Index: 7349358 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.5086. Min Act: -0.1700
Data Index: 3552733 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.4773. Min Act: -0.1700
Data Index: 984698 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.4773. Min Act: -0.1700
Data Index: 796207 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.4773. Min Act: -0.1700
Data Index: 4361782 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.4773. Min Act: -0.1700
Data Index: 1116115 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.4461. Min Act: -0.1700
Data Index: 4902136 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.4461. Min Act: -0.1700
Data Index: 7767344 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.4148. Min Act: -0.1700
Data Index: 8824169 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.4148. Min Act: -0.1700
Data Index: 5365192 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.3836. Min Act: -0.1700
Data Index: 3926659 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6648. Min Range: -5.6648
Max Act: 5.3836. Min Act: -0.1700
Data Index: 7349356 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #19