Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5239 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.5318. Min Act: -0.1700
Data Index: 3379094 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.3443. Min Act: -0.1700
Data Index: 7253743 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.2193. Min Act: -0.1700
Data Index: 756841 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.2818. Min Act: -0.1700
Data Index: 5261971 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.2193. Min Act: -0.1700
Data Index: 5349530 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.2193. Min Act: -0.1700
Data Index: 8674249 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.1568. Min Act: -0.1700
Data Index: 2867306 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.1568. Min Act: -0.1700
Data Index: 4133832 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.1568. Min Act: -0.1700
Data Index: 3530073 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0943. Min Act: -0.1700
Data Index: 5298736 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0943. Min Act: -0.1700
Data Index: 5220514 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0943. Min Act: -0.1700
Data Index: 5166697 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0943. Min Act: -0.1700
Data Index: 6998014 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0318. Min Act: -0.1700
Data Index: 182021 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0318. Min Act: -0.1700
Data Index: 2428283 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0318. Min Act: -0.1700
Data Index: 7902947 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0318. Min Act: -0.1700
Data Index: 5340451 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0318. Min Act: -0.1700
Data Index: 3832519 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5318. Min Range: -9.5318
Max Act: 9.0318. Min Act: -0.1700
Data Index: 4841615 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5318. Min Range: -9.5318
Max Act: 8.9693. Min Act: -0.1700
Data Index: 2664913 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #19