Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 456 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.7178. Min Act: -0.1700
Data Index: 384076 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.7178. Min Act: -0.1700
Data Index: 1117694 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.6865. Min Act: -0.1700
Data Index: 828289 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.6240. Min Act: -0.1700
Data Index: 3566217 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.5928. Min Act: -0.1700
Data Index: 7201152 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.5928. Min Act: -0.1700
Data Index: 3192440 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.5615. Min Act: -0.1700
Data Index: 770197 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.5303. Min Act: -0.1700
Data Index: 4928262 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4990. Min Act: -0.1700
Data Index: 6413393 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4990. Min Act: -0.1700
Data Index: 1521994 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4678. Min Act: -0.1700
Data Index: 2845689 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4678. Min Act: -0.1700
Data Index: 2102678 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4678. Min Act: -0.1700
Data Index: 6413389 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4678. Min Act: -0.1700
Data Index: 4493084 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4365. Min Act: -0.1700
Data Index: 5860584 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4365. Min Act: -0.1700
Data Index: 3868525 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4365. Min Act: -0.1700
Data Index: 3705016 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4365. Min Act: -0.1700
Data Index: 5289404 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4053. Min Act: -0.1700
Data Index: 1770908 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7178. Min Range: -5.7178
Max Act: 5.4053. Min Act: -0.1700
Data Index: 2102673 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19