Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3006 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.7710. Min Act: -0.1700
Data Index: 3206878 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.5835. Min Act: -0.1700
Data Index: 1498308 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.5210. Min Act: -0.1700
Data Index: 615054 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.3335. Min Act: -0.1700
Data Index: 4265840 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.2710. Min Act: -0.1700
Data Index: 7502751 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.2085. Min Act: -0.1700
Data Index: 4164328 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.2710. Min Act: -0.1700
Data Index: 1110277 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.1460. Min Act: -0.1700
Data Index: 7369831 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.0835. Min Act: -0.1700
Data Index: 6394726 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.0835. Min Act: -0.1700
Data Index: 3425561 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.0210. Min Act: -0.1700
Data Index: 8028156 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.0835. Min Act: -0.1700
Data Index: 8679621 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7710. Min Range: -8.7710
Max Act: 8.0210. Min Act: -0.1700
Data Index: 425255 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7710. Min Range: -8.7710
Max Act: 7.9898. Min Act: -0.1700
Data Index: 8497674 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7710. Min Range: -8.7710
Max Act: 7.9273. Min Act: -0.1700
Data Index: 625976 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7710. Min Range: -8.7710
Max Act: 7.9585. Min Act: -0.1700
Data Index: 6362756 (Open Web Text)
Max Activating Token Index: 924
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7710. Min Range: -8.7710
Max Act: 7.9585. Min Act: -0.1700
Data Index: 6794060 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7710. Min Range: -8.7710
Max Act: 7.9273. Min Act: -0.1700
Data Index: 5736627 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7710. Min Range: -8.7710
Max Act: 7.9585. Min Act: -0.1700
Data Index: 2971840 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7710. Min Range: -8.7710
Max Act: 7.8960. Min Act: -0.1700
Data Index: 3063524 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19