Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5893 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.4038. Min Act: -0.1700
Data Index: 5352544 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.3101. Min Act: -0.1700
Data Index: 4138172 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.2163. Min Act: -0.1700
Data Index: 519129 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.2163. Min Act: -0.1700
Data Index: 8442473 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.1538. Min Act: -0.1700
Data Index: 5768018 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.1538. Min Act: -0.1700
Data Index: 1901408 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.0601. Min Act: -0.1700
Data Index: 2618551 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.0601. Min Act: -0.1700
Data Index: 6616181 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4038. Min Range: -7.4038
Max Act: 7.0288. Min Act: -0.1700
Data Index: 787333 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.9663. Min Act: -0.1700
Data Index: 6180577 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.9351. Min Act: -0.1700
Data Index: 638948 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.9351. Min Act: -0.1700
Data Index: 6701005 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.9038. Min Act: -0.1700
Data Index: 4300926 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.8726. Min Act: -0.1700
Data Index: 8682007 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.8726. Min Act: -0.1700
Data Index: 60080 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.8726. Min Act: -0.1700
Data Index: 7169299 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.8413. Min Act: -0.1700
Data Index: 4576659 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.8413. Min Act: -0.1700
Data Index: 8628280 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.8413. Min Act: -0.1700
Data Index: 3187605 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4038. Min Range: -7.4038
Max Act: 6.8101. Min Act: -0.1700
Data Index: 6988114 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #19