Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3943 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.9708. Min Act: -0.1700
Data Index: 3414915 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.9083. Min Act: -0.1700
Data Index: 3836305 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.9395. Min Act: -0.1700
Data Index: 3414917 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8770. Min Act: -0.1700
Data Index: 6256688 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8770. Min Act: -0.1700
Data Index: 834599 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8458. Min Act: -0.1700
Data Index: 3190504 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8458. Min Act: -0.1700
Data Index: 963087 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8458. Min Act: -0.1700
Data Index: 4003170 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8145. Min Act: -0.1700
Data Index: 5519313 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8458. Min Act: -0.1700
Data Index: 2930731 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8145. Min Act: -0.1700
Data Index: 8202898 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8145. Min Act: -0.1700
Data Index: 8065644 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8458. Min Act: -0.1700
Data Index: 654366 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8458. Min Act: -0.1700
Data Index: 2183394 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8145. Min Act: -0.1700
Data Index: 6466452 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8458. Min Act: -0.1700
Data Index: 5867144 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8458. Min Act: -0.1700
Data Index: 499233 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8145. Min Act: -0.1700
Data Index: 3982793 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8145. Min Act: -0.1700
Data Index: 4415408 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9708. Min Range: -4.9708
Max Act: 4.8145. Min Act: -0.1700
Data Index: 932982 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #19