Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3472 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5460. Min Range: -7.5460
Max Act: 7.5460. Min Act: -0.1700
Data Index: 485463 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5460. Min Range: -7.5460
Max Act: 7.1710. Min Act: -0.1700
Data Index: 4126977 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5460. Min Range: -7.5460
Max Act: 7.1085. Min Act: -0.1700
Data Index: 623055 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5460. Min Range: -7.5460
Max Act: 7.0460. Min Act: -0.1700
Data Index: 3628063 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5460. Min Range: -7.5460
Max Act: 7.0460. Min Act: -0.1700
Data Index: 6599352 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5460. Min Range: -7.5460
Max Act: 7.0460. Min Act: -0.1700
Data Index: 3374337 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5460. Min Range: -7.5460
Max Act: 7.0148. Min Act: -0.1700
Data Index: 1110514 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5460. Min Range: -7.5460
Max Act: 7.0148. Min Act: -0.1700
Data Index: 6254945 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.9835. Min Act: -0.1700
Data Index: 6960566 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.9523. Min Act: -0.1700
Data Index: 8551853 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.8898. Min Act: -0.1700
Data Index: 2653903 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.9210. Min Act: -0.1700
Data Index: 8153081 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.8898. Min Act: -0.1700
Data Index: 3473125 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.8898. Min Act: -0.1700
Data Index: 2265034 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.9210. Min Act: -0.1700
Data Index: 3590557 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.8898. Min Act: -0.1700
Data Index: 914889 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.8898. Min Act: -0.1700
Data Index: 4121714 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.8273. Min Act: -0.1700
Data Index: 3983063 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.8585. Min Act: -0.1700
Data Index: 8073432 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5460. Min Range: -7.5460
Max Act: 6.8585. Min Act: -0.1700
Data Index: 6091343 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #19