Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3608 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.9498. Min Act: -0.1700
Data Index: 5812526 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.8560. Min Act: -0.1700
Data Index: 3367917 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.6996. Min Act: -0.1700
Data Index: 8689681 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.6370. Min Act: -0.1700
Data Index: 8056497 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.6683. Min Act: -0.1700
Data Index: 156191 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.6370. Min Act: -0.1700
Data Index: 7409175 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.6370. Min Act: -0.1700
Data Index: 1455381 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.6057. Min Act: -0.1700
Data Index: 5326634 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.6057. Min Act: -0.1700
Data Index: 6926813 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.5744. Min Act: -0.1700
Data Index: 7091390 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.5431. Min Act: -0.1700
Data Index: 8128193 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.5744. Min Act: -0.1700
Data Index: 274492 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.5118. Min Act: -0.1700
Data Index: 3155165 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.5118. Min Act: -0.1700
Data Index: 2866134 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.4961. Min Act: -0.1700
Data Index: 1253764 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.4961. Min Act: -0.1700
Data Index: 1471711 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.4961. Min Act: -0.1700
Data Index: 2558329 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.4961. Min Act: -0.1700
Data Index: 2283812 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.4961. Min Act: -0.1700
Data Index: 355005 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9498. Min Range: -3.9498
Max Act: 3.4804. Min Act: -0.1700
Data Index: 7196462 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #19