Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6366 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.9307. Min Act: -0.1700
Data Index: 1340165 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.8057. Min Act: -0.1700
Data Index: 5752899 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7432. Min Act: -0.1700
Data Index: 1173238 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7432. Min Act: -0.1700
Data Index: 102235 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7745. Min Act: -0.1700
Data Index: 3374868 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7432. Min Act: -0.1700
Data Index: 7033426 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7432. Min Act: -0.1700
Data Index: 4137112 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7432. Min Act: -0.1700
Data Index: 2611124 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7432. Min Act: -0.1700
Data Index: 2083915 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7120. Min Act: -0.1700
Data Index: 8576355 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.7120. Min Act: -0.1700
Data Index: 5521741 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.6807. Min Act: -0.1700
Data Index: 6537501 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.6495. Min Act: -0.1700
Data Index: 3250994 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.6495. Min Act: -0.1700
Data Index: 300425 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.6495. Min Act: -0.1700
Data Index: 3104613 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.6182. Min Act: -0.1700
Data Index: 4447961 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.5870. Min Act: -0.1700
Data Index: 2664994 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.5870. Min Act: -0.1700
Data Index: 6413449 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.6182. Min Act: -0.1700
Data Index: 3308494 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9307. Min Range: -5.9307
Max Act: 5.5557. Min Act: -0.1700
Data Index: 7012665 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #19