Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2038 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2471. Min Range: -9.2471
Max Act: 9.2471. Min Act: -0.1700
Data Index: 2356133 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2471. Min Range: -9.2471
Max Act: 9.1846. Min Act: -0.1700
Data Index: 7209553 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.8721. Min Act: -0.1700
Data Index: 806805 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.8721. Min Act: -0.1700
Data Index: 6958112 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.8096. Min Act: -0.1700
Data Index: 8310369 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.7471. Min Act: -0.1700
Data Index: 7564717 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6846. Min Act: -0.1700
Data Index: 8641631 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6846. Min Act: -0.1700
Data Index: 2781414 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6846. Min Act: -0.1700
Data Index: 8291485 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 4056611 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 8691334 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 4253423 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 4706968 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 8140607 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 6775843 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 6131458 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 4369043 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.6221. Min Act: -0.1700
Data Index: 1690117 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.5596. Min Act: -0.1700
Data Index: 5839894 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2471. Min Range: -9.2471
Max Act: 8.5596. Min Act: -0.1700
Data Index: 5558893 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #19