Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3649 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.7774. Min Act: -0.1700
Data Index: 2637822 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.7774. Min Act: -0.1700
Data Index: 3410815 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.7774. Min Act: -0.1700
Data Index: 288025 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.7462. Min Act: -0.1700
Data Index: 3735901 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.7462. Min Act: -0.1700
Data Index: 4341378 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.7462. Min Act: -0.1700
Data Index: 8768537 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.7149. Min Act: -0.1700
Data Index: 5400351 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.7149. Min Act: -0.1700
Data Index: 724325 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.6837. Min Act: -0.1700
Data Index: 5091316 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.6837. Min Act: -0.1700
Data Index: 1748297 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.6524. Min Act: -0.1700
Data Index: 777586 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.6837. Min Act: -0.1700
Data Index: 7426242 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.6524. Min Act: -0.1700
Data Index: 1603165 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.6837. Min Act: -0.1700
Data Index: 804421 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.6524. Min Act: -0.1700
Data Index: 1195630 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.5899. Min Act: -0.1700
Data Index: 2747449 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.6212. Min Act: -0.1700
Data Index: 4672065 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.5899. Min Act: -0.1700
Data Index: 5807582 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.5899. Min Act: -0.1700
Data Index: 8370160 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7774. Min Range: -6.7774
Max Act: 6.5899. Min Act: -0.1700
Data Index: 1100517 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19