Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 521 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.7973. Min Act: -0.1700
Data Index: 6263245 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.6411. Min Act: -0.1700
Data Index: 7177672 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.5473. Min Act: -0.1700
Data Index: 4576115 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.5786. Min Act: -0.1700
Data Index: 5971394 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.6098. Min Act: -0.1700
Data Index: 1694179 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.5473. Min Act: -0.1700
Data Index: 7767848 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.5161. Min Act: -0.1700
Data Index: 5931396 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.5161. Min Act: -0.1700
Data Index: 1623787 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.5161. Min Act: -0.1700
Data Index: 7022704 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4848. Min Act: -0.1700
Data Index: 4665278 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4848. Min Act: -0.1700
Data Index: 2891238 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4536. Min Act: -0.1700
Data Index: 5733622 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4848. Min Act: -0.1700
Data Index: 1097920 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4223. Min Act: -0.1700
Data Index: 6835377 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4536. Min Act: -0.1700
Data Index: 3128501 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4536. Min Act: -0.1700
Data Index: 4201434 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4536. Min Act: -0.1700
Data Index: 3440745 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4536. Min Act: -0.1700
Data Index: 4721082 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4223. Min Act: -0.1700
Data Index: 5868661 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7973. Min Range: -4.7973
Max Act: 4.4223. Min Act: -0.1700
Data Index: 861401 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #19