Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 686 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.9720. Min Act: -0.1700
Data Index: 2699251 (Open Web Text)
Max Activating Token Index: 138
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.6749. Min Act: -0.1700
Data Index: 7001168 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.6749. Min Act: -0.1700
Data Index: 6817168 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.6436. Min Act: -0.1700
Data Index: 6585821 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.6123. Min Act: -0.1700
Data Index: 5320488 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.5966. Min Act: -0.1700
Data Index: 7328918 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.5810. Min Act: -0.1700
Data Index: 3203250 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.5027. Min Act: -0.1700
Data Index: 2377384 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4714. Min Act: -0.1700
Data Index: 2988925 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.5027. Min Act: -0.1700
Data Index: 435384 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4714. Min Act: -0.1700
Data Index: 2529248 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4714. Min Act: -0.1700
Data Index: 4965302 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4557. Min Act: -0.1700
Data Index: 2944774 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4557. Min Act: -0.1700
Data Index: 8346318 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4557. Min Act: -0.1700
Data Index: 4640208 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4400. Min Act: -0.1700
Data Index: 6739017 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4400. Min Act: -0.1700
Data Index: 2790115 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4243. Min Act: -0.1700
Data Index: 5676985 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4243. Min Act: -0.1700
Data Index: 6331776 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9720. Min Range: -3.9720
Max Act: 3.4243. Min Act: -0.1700
Data Index: 6377707 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #19