Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2941 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.6906. Min Act: -0.1700
Data Index: 811617 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.5031. Min Act: -0.1700
Data Index: 4296133 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.2531. Min Act: -0.1700
Data Index: 8320046 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.1281. Min Act: -0.1700
Data Index: 4962252 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.0031. Min Act: -0.1700
Data Index: 2892994 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.0656. Min Act: -0.1700
Data Index: 5060552 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.0656. Min Act: -0.1700
Data Index: 8200408 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.0031. Min Act: -0.1700
Data Index: 5214457 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.0031. Min Act: -0.1700
Data Index: 6611670 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.6906. Min Range: -9.6906
Max Act: 9.0031. Min Act: -0.1700
Data Index: 6977159 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.9406. Min Act: -0.1700
Data Index: 8166742 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.8781. Min Act: -0.1700
Data Index: 4657692 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 1109678 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.7531. Min Act: -0.1700
Data Index: 6979949 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 5044422 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 4098128 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 8731099 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 1840887 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.8156. Min Act: -0.1700
Data Index: 3623515 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.6906. Min Range: -9.6906
Max Act: 8.7531. Min Act: -0.1700
Data Index: 6565533 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #19