Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 508 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.3770. Min Act: -0.1700
Data Index: 2350169 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.2208. Min Act: -0.1700
Data Index: 6326577 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.1270. Min Act: -0.1700
Data Index: 7755365 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.0958. Min Act: -0.1700
Data Index: 309900 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.1270. Min Act: -0.1700
Data Index: 6716043 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.0958. Min Act: -0.1700
Data Index: 5185883 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.0333. Min Act: -0.1700
Data Index: 699483 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.0333. Min Act: -0.1700
Data Index: 7160216 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.0333. Min Act: -0.1700
Data Index: 1197884 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.0333. Min Act: -0.1700
Data Index: 6321891 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9708. Min Act: -0.1700
Data Index: 1524978 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9708. Min Act: -0.1700
Data Index: 8370887 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9708. Min Act: -0.1700
Data Index: 5266820 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9708. Min Act: -0.1700
Data Index: 294821 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9708. Min Act: -0.1700
Data Index: 4829983 (Open Web Text)
Max Activating Token Index: 66
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9708. Min Act: -0.1700
Data Index: 3208787 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3770. Min Range: -5.3770
Max Act: 5.0020. Min Act: -0.1700
Data Index: 3949160 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9708. Min Act: -0.1700
Data Index: 294822 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9395. Min Act: -0.1700
Data Index: 7872132 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3770. Min Range: -5.3770
Max Act: 4.9083. Min Act: -0.1700
Data Index: 7599347 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #19