Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2454 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7391. Min Range: -7.7391
Max Act: 7.7391. Min Act: -0.1700
Data Index: 8424311 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7391. Min Range: -7.7391
Max Act: 7.5204. Min Act: -0.1700
Data Index: 5455245 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7391. Min Range: -7.7391
Max Act: 7.3954. Min Act: -0.1700
Data Index: 6693538 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7391. Min Range: -7.7391
Max Act: 7.0829. Min Act: -0.1700
Data Index: 7355121 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7391. Min Range: -7.7391
Max Act: 7.0829. Min Act: -0.1700
Data Index: 4695906 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.9266. Min Act: -0.1700
Data Index: 3378043 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.8641. Min Act: -0.1700
Data Index: 7356503 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.8641. Min Act: -0.1700
Data Index: 7339564 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.8641. Min Act: -0.1700
Data Index: 1795116 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.8329. Min Act: -0.1700
Data Index: 3079564 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.8016. Min Act: -0.1700
Data Index: 3196861 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.7704. Min Act: -0.1700
Data Index: 5244556 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.8016. Min Act: -0.1700
Data Index: 2486674 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.7704. Min Act: -0.1700
Data Index: 5554457 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.7391. Min Act: -0.1700
Data Index: 7851990 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.7391. Min Act: -0.1700
Data Index: 4807620 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.7391. Min Act: -0.1700
Data Index: 2974596 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.7704. Min Act: -0.1700
Data Index: 5328342 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.7704. Min Act: -0.1700
Data Index: 3209081 (Open Web Text)
Max Activating Token Index: 655
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7391. Min Range: -7.7391
Max Act: 6.7391. Min Act: -0.1700
Data Index: 196568 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19