Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1427 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.0293. Min Range: -5.0293
Max Act: 5.0293. Min Act: -0.1700
Data Index: 7193161 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.9356. Min Act: -0.1700
Data Index: 3358496 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.9356. Min Act: -0.1700
Data Index: 4323814 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8731. Min Act: -0.1700
Data Index: 246666 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8418. Min Act: -0.1700
Data Index: 1074275 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8418. Min Act: -0.1700
Data Index: 1826770 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8731. Min Act: -0.1700
Data Index: 1054403 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8418. Min Act: -0.1700
Data Index: 8400629 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8106. Min Act: -0.1700
Data Index: 7265457 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8106. Min Act: -0.1700
Data Index: 2971374 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8731. Min Act: -0.1700
Data Index: 7227937 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8731. Min Act: -0.1700
Data Index: 2678737 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8106. Min Act: -0.1700
Data Index: 59766 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.7793. Min Act: -0.1700
Data Index: 4681403 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8106. Min Act: -0.1700
Data Index: 6378084 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8106. Min Act: -0.1700
Data Index: 551102 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8106. Min Act: -0.1700
Data Index: 1447319 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.7793. Min Act: -0.1700
Data Index: 54416 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.8106. Min Act: -0.1700
Data Index: 561457 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0293. Min Range: -5.0293
Max Act: 4.7793. Min Act: -0.1700
Data Index: 3424945 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #19