Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3566 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2132. Min Range: -6.2132
Max Act: 6.2132. Min Act: -0.1700
Data Index: 148710 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.9007. Min Act: -0.1700
Data Index: 4546235 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8695. Min Act: -0.1700
Data Index: 3599953 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8382. Min Act: -0.1700
Data Index: 3575867 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8382. Min Act: -0.1700
Data Index: 685716 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.8070. Min Act: -0.1700
Data Index: 779619 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.7445. Min Act: -0.1700
Data Index: 4953560 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.7132. Min Act: -0.1700
Data Index: 7420827 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.6820. Min Act: -0.1700
Data Index: 5524661 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.6820. Min Act: -0.1700
Data Index: 2042373 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.6820. Min Act: -0.1700
Data Index: 7059064 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.6507. Min Act: -0.1700
Data Index: 8605715 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.6195. Min Act: -0.1700
Data Index: 5428008 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.6195. Min Act: -0.1700
Data Index: 3319303 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.5570. Min Act: -0.1700
Data Index: 7660163 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.5570. Min Act: -0.1700
Data Index: 7613156 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.5882. Min Act: -0.1700
Data Index: 8008921 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.5570. Min Act: -0.1700
Data Index: 178218 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.5882. Min Act: -0.1700
Data Index: 486775 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2132. Min Range: -6.2132
Max Act: 5.5882. Min Act: -0.1700
Data Index: 4474217 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19