Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 913 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.1987. Min Act: -0.1700
Data Index: 7983638 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.1050. Min Act: -0.1700
Data Index: 3814256 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.0737. Min Act: -0.1700
Data Index: 5725625 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.0737. Min Act: -0.1700
Data Index: 6572928 (Open Web Text)
Max Activating Token Index: 263
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.0425. Min Act: -0.1700
Data Index: 4661584 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.0425. Min Act: -0.1700
Data Index: 8291895 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.0425. Min Act: -0.1700
Data Index: 3966754 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.0112. Min Act: -0.1700
Data Index: 8790592 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1987. Min Range: -4.1987
Max Act: 4.0112. Min Act: -0.1700
Data Index: 409932 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9799. Min Act: -0.1700
Data Index: 6076774 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9799. Min Act: -0.1700
Data Index: 604489 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9799. Min Act: -0.1700
Data Index: 6228498 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9487. Min Act: -0.1700
Data Index: 3801055 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9799. Min Act: -0.1700
Data Index: 6974530 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9487. Min Act: -0.1700
Data Index: 153196 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9487. Min Act: -0.1700
Data Index: 5919973 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9487. Min Act: -0.1700
Data Index: 7666377 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9487. Min Act: -0.1700
Data Index: 3130795 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9174. Min Act: -0.1700
Data Index: 3516431 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1987. Min Range: -4.1987
Max Act: 3.9174. Min Act: -0.1700
Data Index: 2669574 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #19