Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5434 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.8245. Min Act: -0.1700
Data Index: 3457160 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.7933. Min Act: -0.1700
Data Index: 3157322 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.7620. Min Act: -0.1700
Data Index: 6137975 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.7308. Min Act: -0.1700
Data Index: 5652510 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.6683. Min Act: -0.1700
Data Index: 3678639 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.6370. Min Act: -0.1700
Data Index: 1852095 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.5120. Min Act: -0.1700
Data Index: 264931 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.4808. Min Act: -0.1700
Data Index: 831644 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.4808. Min Act: -0.1700
Data Index: 1289502 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.4495. Min Act: -0.1700
Data Index: 249952 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.3870. Min Act: -0.1700
Data Index: 3099419 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.3558. Min Act: -0.1700
Data Index: 377393 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.3245. Min Act: -0.1700
Data Index: 482158 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.3245. Min Act: -0.1700
Data Index: 4912822 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.3245. Min Act: -0.1700
Data Index: 5980615 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.3245. Min Act: -0.1700
Data Index: 8179133 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.2620. Min Act: -0.1700
Data Index: 6761692 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.2933. Min Act: -0.1700
Data Index: 7305 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.2620. Min Act: -0.1700
Data Index: 6969763 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8245. Min Range: -6.8245
Max Act: 6.2308. Min Act: -0.1700
Data Index: 5673950 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #19