Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 51 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.5120. Min Act: -0.1700
Data Index: 6644835 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.3870. Min Act: -0.1700
Data Index: 5232693 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.3558. Min Act: -0.1700
Data Index: 8827924 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.3558. Min Act: -0.1700
Data Index: 3001037 (Open Web Text)
Max Activating Token Index: 284
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2933. Min Act: -0.1700
Data Index: 2592876 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2620. Min Act: -0.1700
Data Index: 6211326 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2933. Min Act: -0.1700
Data Index: 6642362 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2933. Min Act: -0.1700
Data Index: 1053310 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2620. Min Act: -0.1700
Data Index: 4840229 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2308. Min Act: -0.1700
Data Index: 3816285 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2308. Min Act: -0.1700
Data Index: 5573991 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2620. Min Act: -0.1700
Data Index: 6169180 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2620. Min Act: -0.1700
Data Index: 6121134 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2308. Min Act: -0.1700
Data Index: 5543664 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.1995. Min Act: -0.1700
Data Index: 2545398 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.2308. Min Act: -0.1700
Data Index: 7902213 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.1995. Min Act: -0.1700
Data Index: 6803444 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.1683. Min Act: -0.1700
Data Index: 2129549 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.1683. Min Act: -0.1700
Data Index: 6847096 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5120. Min Range: -5.5120
Max Act: 5.1995. Min Act: -0.1700
Data Index: 808643 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #19