Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3345 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1176. Min Range: -7.1176
Max Act: 7.1176. Min Act: -0.1700
Data Index: 8358430 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.6488. Min Act: -0.1700
Data Index: 104932 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.5863. Min Act: -0.1700
Data Index: 620711 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.5238. Min Act: -0.1700
Data Index: 6865968 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.4926. Min Act: -0.1700
Data Index: 5256848 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.4613. Min Act: -0.1700
Data Index: 7037185 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.3051. Min Act: -0.1700
Data Index: 3679258 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.3363. Min Act: -0.1700
Data Index: 7759667 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.3363. Min Act: -0.1700
Data Index: 4875059 (Open Web Text)
Max Activating Token Index: 188
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.3363. Min Act: -0.1700
Data Index: 3300995 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2738. Min Act: -0.1700
Data Index: 2427834 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2738. Min Act: -0.1700
Data Index: 4545746 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2426. Min Act: -0.1700
Data Index: 6382188 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2426. Min Act: -0.1700
Data Index: 7085318 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2426. Min Act: -0.1700
Data Index: 8689562 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2426. Min Act: -0.1700
Data Index: 1201847 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2426. Min Act: -0.1700
Data Index: 2788952 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2426. Min Act: -0.1700
Data Index: 413393 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2113. Min Act: -0.1700
Data Index: 7100097 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1176. Min Range: -7.1176
Max Act: 6.2113. Min Act: -0.1700
Data Index: 2569252 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #19