Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 380 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1262. Min Range: -6.1262
Max Act: 6.1262. Min Act: -0.1700
Data Index: 7463743 (Open Web Text)
Max Activating Token Index: 214
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1262. Min Range: -6.1262
Max Act: 6.0637. Min Act: -0.1700
Data Index: 5756002 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1262. Min Range: -6.1262
Max Act: 6.0325. Min Act: -0.1700
Data Index: 3987465 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1262. Min Range: -6.1262
Max Act: 6.0325. Min Act: -0.1700
Data Index: 8641099 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1262. Min Range: -6.1262
Max Act: 6.0012. Min Act: -0.1700
Data Index: 173108 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.9700. Min Act: -0.1700
Data Index: 7323535 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.9387. Min Act: -0.1700
Data Index: 2099991 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8762. Min Act: -0.1700
Data Index: 7361652 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8762. Min Act: -0.1700
Data Index: 416617 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8450. Min Act: -0.1700
Data Index: 232452 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8450. Min Act: -0.1700
Data Index: 5305897 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8137. Min Act: -0.1700
Data Index: 2300151 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8137. Min Act: -0.1700
Data Index: 7130029 (Open Web Text)
Max Activating Token Index: 205
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8137. Min Act: -0.1700
Data Index: 6216299 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8137. Min Act: -0.1700
Data Index: 1054742 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8450. Min Act: -0.1700
Data Index: 2256345 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.8137. Min Act: -0.1700
Data Index: 903233 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.7825. Min Act: -0.1700
Data Index: 5083932 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.7825. Min Act: -0.1700
Data Index: 2320586 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1262. Min Range: -6.1262
Max Act: 5.7512. Min Act: -0.1700
Data Index: 2886518 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #19