Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4620 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6132. Min Range: -8.6132
Max Act: 8.6132. Min Act: -0.1700
Data Index: 5362758 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6132. Min Range: -8.6132
Max Act: 8.2382. Min Act: -0.1700
Data Index: 5726097 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6132. Min Range: -8.6132
Max Act: 8.0819. Min Act: -0.1700
Data Index: 8109671 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6132. Min Range: -8.6132
Max Act: 8.0819. Min Act: -0.1700
Data Index: 5988507 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6132. Min Range: -8.6132
Max Act: 8.0507. Min Act: -0.1700
Data Index: 4400089 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6132. Min Range: -8.6132
Max Act: 8.0819. Min Act: -0.1700
Data Index: 4006728 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.9882. Min Act: -0.1700
Data Index: 233477 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.9569. Min Act: -0.1700
Data Index: 5393171 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8944. Min Act: -0.1700
Data Index: 4273724 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8944. Min Act: -0.1700
Data Index: 3729289 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8944. Min Act: -0.1700
Data Index: 1054629 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.9257. Min Act: -0.1700
Data Index: 2897561 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8944. Min Act: -0.1700
Data Index: 6908288 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8944. Min Act: -0.1700
Data Index: 6657648 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8632. Min Act: -0.1700
Data Index: 6443919 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8319. Min Act: -0.1700
Data Index: 2723405 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8632. Min Act: -0.1700
Data Index: 2557780 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8007. Min Act: -0.1700
Data Index: 720851 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8007. Min Act: -0.1700
Data Index: 6261781 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6132. Min Range: -8.6132
Max Act: 7.8007. Min Act: -0.1700
Data Index: 5692923 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #19