Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3153 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.6324. Min Act: -0.1700
Data Index: 6915797 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.3511. Min Act: -0.1700
Data Index: 4190680 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.3199. Min Act: -0.1700
Data Index: 7404498 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.3511. Min Act: -0.1700
Data Index: 7775970 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.3199. Min Act: -0.1700
Data Index: 1373233 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.3199. Min Act: -0.1700
Data Index: 7267057 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.2886. Min Act: -0.1700
Data Index: 4996711 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.2574. Min Act: -0.1700
Data Index: 6031901 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.1949. Min Act: -0.1700
Data Index: 7542839 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.1324. Min Act: -0.1700
Data Index: 303781 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.1011. Min Act: -0.1700
Data Index: 894593 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.1011. Min Act: -0.1700
Data Index: 628523 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0699. Min Act: -0.1700
Data Index: 1979304 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0699. Min Act: -0.1700
Data Index: 2747033 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0699. Min Act: -0.1700
Data Index: 672945 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0699. Min Act: -0.1700
Data Index: 5220168 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0386. Min Act: -0.1700
Data Index: 6973423 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0386. Min Act: -0.1700
Data Index: 6033195 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0386. Min Act: -0.1700
Data Index: 8440915 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6324. Min Range: -6.6324
Max Act: 6.0074. Min Act: -0.1700
Data Index: 7692775 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #19