Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 812 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.8992. Min Act: -0.1700
Data Index: 1454074 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.8055. Min Act: -0.1700
Data Index: 1350452 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.6492. Min Act: -0.1700
Data Index: 8749895 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.6180. Min Act: -0.1700
Data Index: 8411985 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.6180. Min Act: -0.1700
Data Index: 6301958 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5867. Min Act: -0.1700
Data Index: 3514397 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5867. Min Act: -0.1700
Data Index: 3589436 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5867. Min Act: -0.1700
Data Index: 274486 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5867. Min Act: -0.1700
Data Index: 6323277 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5555. Min Act: -0.1700
Data Index: 2183808 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5555. Min Act: -0.1700
Data Index: 689279 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5555. Min Act: -0.1700
Data Index: 859981 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5555. Min Act: -0.1700
Data Index: 5819800 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5555. Min Act: -0.1700
Data Index: 4577300 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5555. Min Act: -0.1700
Data Index: 4620220 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5242. Min Act: -0.1700
Data Index: 7205033 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.4930. Min Act: -0.1700
Data Index: 2092933 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5242. Min Act: -0.1700
Data Index: 5037250 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.4930. Min Act: -0.1700
Data Index: 18932 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.8992. Min Range: -4.8992
Max Act: 4.5555. Min Act: -0.1700
Data Index: 8578397 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #19