Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 224 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1958. Min Range: -5.1958
Max Act: 5.1958. Min Act: -0.1700
Data Index: 1362668 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1958. Min Range: -5.1958
Max Act: 5.1020. Min Act: -0.1700
Data Index: 8732427 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1958. Min Range: -5.1958
Max Act: 5.0708. Min Act: -0.1700
Data Index: 470023 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1958. Min Range: -5.1958
Max Act: 5.0395. Min Act: -0.1700
Data Index: 7200142 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1958. Min Range: -5.1958
Max Act: 5.0083. Min Act: -0.1700
Data Index: 3431451 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9458. Min Act: -0.1700
Data Index: 6744822 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 1942462 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 4539597 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9458. Min Act: -0.1700
Data Index: 6879954 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9458. Min Act: -0.1700
Data Index: 123417 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 1713597 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 4866999 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9458. Min Act: -0.1700
Data Index: 6375509 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 8455373 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 6102873 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 4326201 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9458. Min Act: -0.1700
Data Index: 188417 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 4006482 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 3933435 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1958. Min Range: -5.1958
Max Act: 4.9770. Min Act: -0.1700
Data Index: 3686923 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19