Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2928 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.9645. Min Act: -0.1700
Data Index: 4959322 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.9645. Min Act: -0.1700
Data Index: 3554136 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.7770. Min Act: -0.1700
Data Index: 6200438 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.6520. Min Act: -0.1700
Data Index: 1419116 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.5895. Min Act: -0.1700
Data Index: 642097 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.5895. Min Act: -0.1700
Data Index: 2038772 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.4645. Min Act: -0.1700
Data Index: 6895180 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.4020. Min Act: -0.1700
Data Index: 7293668 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.4020. Min Act: -0.1700
Data Index: 5161376 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9645. Min Range: -9.9645
Max Act: 9.1520. Min Act: -0.1700
Data Index: 7018983 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.9645. Min Act: -0.1700
Data Index: 5238986 (Open Web Text)
Max Activating Token Index: 927
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.9020. Min Act: -0.1700
Data Index: 2806982 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.8395. Min Act: -0.1700
Data Index: 8669507 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.7770. Min Act: -0.1700
Data Index: 1071336 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.7145. Min Act: -0.1700
Data Index: 6211602 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.6520. Min Act: -0.1700
Data Index: 6237729 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.7145. Min Act: -0.1700
Data Index: 6744658 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.6520. Min Act: -0.1700
Data Index: 3195531 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.5895. Min Act: -0.1700
Data Index: 5983093 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9645. Min Range: -9.9645
Max Act: 8.5270. Min Act: -0.1700
Data Index: 5549052 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #19