Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2829 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2922. Min Range: -8.2922
Max Act: 8.2922. Min Act: -0.1700
Data Index: 6569617 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2922. Min Range: -8.2922
Max Act: 8.0422. Min Act: -0.1700
Data Index: 5037461 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.9797. Min Act: -0.1700
Data Index: 2061137 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.9172. Min Act: -0.1700
Data Index: 110525 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.9172. Min Act: -0.1700
Data Index: 2321868 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.9172. Min Act: -0.1700
Data Index: 8327150 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.9797. Min Act: -0.1700
Data Index: 3231293 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.8547. Min Act: -0.1700
Data Index: 8433848 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.7922. Min Act: -0.1700
Data Index: 1512080 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.6985. Min Act: -0.1700
Data Index: 7159532 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.6985. Min Act: -0.1700
Data Index: 6509042 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.6672. Min Act: -0.1700
Data Index: 5852518 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.6672. Min Act: -0.1700
Data Index: 6552019 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.6360. Min Act: -0.1700
Data Index: 1550390 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.6047. Min Act: -0.1700
Data Index: 101260 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.5735. Min Act: -0.1700
Data Index: 7778147 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.5735. Min Act: -0.1700
Data Index: 1854126 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.5735. Min Act: -0.1700
Data Index: 5877786 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.5422. Min Act: -0.1700
Data Index: 5334553 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2922. Min Range: -8.2922
Max Act: 7.4797. Min Act: -0.1700
Data Index: 339834 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #19