Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3831 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1793. Min Range: -10.1793
Max Act: 10.1793. Min Act: -0.1700
Data Index: 7303933 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.8668. Min Act: -0.1700
Data Index: 7362049 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.8668. Min Act: -0.1700
Data Index: 2161586 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.7418. Min Act: -0.1700
Data Index: 687861 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.6168. Min Act: -0.1700
Data Index: 8185262 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.5543. Min Act: -0.1700
Data Index: 2512398 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.5543. Min Act: -0.1700
Data Index: 7221005 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4918. Min Act: -0.1700
Data Index: 4549187 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4918. Min Act: -0.1700
Data Index: 3547823 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4918. Min Act: -0.1700
Data Index: 932423 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4918. Min Act: -0.1700
Data Index: 7894013 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.3668. Min Act: -0.1700
Data Index: 3957448 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4293. Min Act: -0.1700
Data Index: 1249623 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4293. Min Act: -0.1700
Data Index: 7685612 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4293. Min Act: -0.1700
Data Index: 6581328 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4293. Min Act: -0.1700
Data Index: 4956206 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.4293. Min Act: -0.1700
Data Index: 4619131 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.3668. Min Act: -0.1700
Data Index: 3906045 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.3668. Min Act: -0.1700
Data Index: 2307304 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1793. Min Range: -10.1793
Max Act: 9.3668. Min Act: -0.1700
Data Index: 1984377 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #19