Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2926 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.4815. Min Act: -0.1700
Data Index: 3843433 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.2940. Min Act: -0.1700
Data Index: 4562482 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.1690. Min Act: -0.1700
Data Index: 5574745 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.1377. Min Act: -0.1700
Data Index: 1480316 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.1377. Min Act: -0.1700
Data Index: 6242948 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.1377. Min Act: -0.1700
Data Index: 4769948 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.1377. Min Act: -0.1700
Data Index: 7183907 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.1377. Min Act: -0.1700
Data Index: 7062268 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.1065. Min Act: -0.1700
Data Index: 5174393 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0752. Min Act: -0.1700
Data Index: 2843709 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0752. Min Act: -0.1700
Data Index: 5749887 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0440. Min Act: -0.1700
Data Index: 8537885 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0440. Min Act: -0.1700
Data Index: 2409674 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0440. Min Act: -0.1700
Data Index: 6471720 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0127. Min Act: -0.1700
Data Index: 6936476 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0127. Min Act: -0.1700
Data Index: 836746 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0127. Min Act: -0.1700
Data Index: 6105256 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0127. Min Act: -0.1700
Data Index: 5174392 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0440. Min Act: -0.1700
Data Index: 2903955 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.4815. Min Range: -4.4815
Max Act: 4.0127. Min Act: -0.1700
Data Index: 8001777 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #19