Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3951 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.7512. Min Act: -0.1700
Data Index: 4894691 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.6262. Min Act: -0.1700
Data Index: 7092368 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.5637. Min Act: -0.1700
Data Index: 1965977 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.5324. Min Act: -0.1700
Data Index: 5167632 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.5637. Min Act: -0.1700
Data Index: 95703 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.5012. Min Act: -0.1700
Data Index: 6999640 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4699. Min Act: -0.1700
Data Index: 8001518 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.5012. Min Act: -0.1700
Data Index: 5169434 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4074. Min Act: -0.1700
Data Index: 693680 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4074. Min Act: -0.1700
Data Index: 907716 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4074. Min Act: -0.1700
Data Index: 7714139 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.4074. Min Act: -0.1700
Data Index: 2869182 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.3762. Min Act: -0.1700
Data Index: 5404142 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.3762. Min Act: -0.1700
Data Index: 1775574 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.3449. Min Act: -0.1700
Data Index: 6849985 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.3137. Min Act: -0.1700
Data Index: 1926116 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2824. Min Act: -0.1700
Data Index: 756641 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2824. Min Act: -0.1700
Data Index: 3227730 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2512. Min Act: -0.1700
Data Index: 4349006 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7512. Min Range: -6.7512
Max Act: 6.2824. Min Act: -0.1700
Data Index: 4018344 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #19