Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2386 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.9385. Min Act: -0.1700
Data Index: 1331886 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.8760. Min Act: -0.1700
Data Index: 6362688 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.8135. Min Act: -0.1700
Data Index: 175277 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.6885. Min Act: -0.1700
Data Index: 8604605 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.6885. Min Act: -0.1700
Data Index: 2734773 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.6260. Min Act: -0.1700
Data Index: 4184973 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.6260. Min Act: -0.1700
Data Index: 4138890 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.6260. Min Act: -0.1700
Data Index: 6544975 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.6260. Min Act: -0.1700
Data Index: 5458406 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.5635. Min Act: -0.1700
Data Index: 4944174 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.5635. Min Act: -0.1700
Data Index: 7215378 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.5635. Min Act: -0.1700
Data Index: 1200556 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.5635. Min Act: -0.1700
Data Index: 2720522 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.5635. Min Act: -0.1700
Data Index: 7130258 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.5010. Min Act: -0.1700
Data Index: 5989429 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.4385. Min Act: -0.1700
Data Index: 1674526 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.3135. Min Act: -0.1700
Data Index: 7135142 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.3760. Min Act: -0.1700
Data Index: 2830270 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.3760. Min Act: -0.1700
Data Index: 5149689 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.9385. Min Range: -8.9385
Max Act: 8.3760. Min Act: -0.1700
Data Index: 730468 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #19