Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1635 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.3036. Min Act: -0.1700
Data Index: 2646607 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.2098. Min Act: -0.1700
Data Index: 5855507 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.2098. Min Act: -0.1700
Data Index: 4676521 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.1473. Min Act: -0.1700
Data Index: 2984979 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.1161. Min Act: -0.1700
Data Index: 6687877 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.1161. Min Act: -0.1700
Data Index: 1170670 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.0536. Min Act: -0.1700
Data Index: 1800023 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.1161. Min Act: -0.1700
Data Index: 756581 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.0223. Min Act: -0.1700
Data Index: 7402135 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.0536. Min Act: -0.1700
Data Index: 7322671 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.0536. Min Act: -0.1700
Data Index: 4502919 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.0223. Min Act: -0.1700
Data Index: 3335596 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.0223. Min Act: -0.1700
Data Index: 4360237 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.0223. Min Act: -0.1700
Data Index: 7955903 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3036. Min Range: -5.3036
Max Act: 4.9911. Min Act: -0.1700
Data Index: 275459 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3036. Min Range: -5.3036
Max Act: 4.9911. Min Act: -0.1700
Data Index: 859760 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3036. Min Range: -5.3036
Max Act: 4.9911. Min Act: -0.1700
Data Index: 3422772 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3036. Min Range: -5.3036
Max Act: 5.0223. Min Act: -0.1700
Data Index: 1416677 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3036. Min Range: -5.3036
Max Act: 4.9911. Min Act: -0.1700
Data Index: 7719027 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3036. Min Range: -5.3036
Max Act: 4.9911. Min Act: -0.1700
Data Index: 5837267 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #19