Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1643 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1352. Min Act: -0.1700
Data Index: 184525 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.1040. Min Act: -0.1700
Data Index: 4522762 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.0415. Min Act: -0.1700
Data Index: 1221388 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1352. Min Range: -6.1352
Max Act: 6.0415. Min Act: -0.1700
Data Index: 1490254 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9790. Min Act: -0.1700
Data Index: 3290682 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9790. Min Act: -0.1700
Data Index: 6128849 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.9165. Min Act: -0.1700
Data Index: 2349020 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8852. Min Act: -0.1700
Data Index: 7243123 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8540. Min Act: -0.1700
Data Index: 4024829 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8227. Min Act: -0.1700
Data Index: 196202 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.8540. Min Act: -0.1700
Data Index: 1518300 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7602. Min Act: -0.1700
Data Index: 20947 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7602. Min Act: -0.1700
Data Index: 1780121 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7290. Min Act: -0.1700
Data Index: 5757322 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.7290. Min Act: -0.1700
Data Index: 1134650 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6977. Min Act: -0.1700
Data Index: 348321 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6665. Min Act: -0.1700
Data Index: 1910768 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 7071647 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 8730819 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1352. Min Range: -6.1352
Max Act: 5.6352. Min Act: -0.1700
Data Index: 2853709 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #19