Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1743 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.9305. Min Act: -0.1700
Data Index: 7759680 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.8680. Min Act: -0.1700
Data Index: 3205443 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.7742. Min Act: -0.1700
Data Index: 6745486 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.7430. Min Act: -0.1700
Data Index: 3014645 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.7430. Min Act: -0.1700
Data Index: 2693280 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.7430. Min Act: -0.1700
Data Index: 7494223 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6805. Min Act: -0.1700
Data Index: 2041354 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6805. Min Act: -0.1700
Data Index: 4592041 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6492. Min Act: -0.1700
Data Index: 8376522 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6180. Min Act: -0.1700
Data Index: 5449838 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5867. Min Act: -0.1700
Data Index: 6182236 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.6180. Min Act: -0.1700
Data Index: 5749755 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5555. Min Act: -0.1700
Data Index: 4954038 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5555. Min Act: -0.1700
Data Index: 6579111 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5555. Min Act: -0.1700
Data Index: 677750 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5555. Min Act: -0.1700
Data Index: 4572272 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5555. Min Act: -0.1700
Data Index: 609250 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5242. Min Act: -0.1700
Data Index: 6985163 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5242. Min Act: -0.1700
Data Index: 1408997 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9305. Min Range: -6.9305
Max Act: 6.5242. Min Act: -0.1700
Data Index: 5199025 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #19