Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3108 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1021. Min Range: -7.1021
Max Act: 7.1021. Min Act: -0.1700
Data Index: 2820724 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1021. Min Range: -7.1021
Max Act: 7.0083. Min Act: -0.1700
Data Index: 5296589 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1021. Min Range: -7.1021
Max Act: 7.0083. Min Act: -0.1700
Data Index: 8232637 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.9458. Min Act: -0.1700
Data Index: 8501671 (Open Web Text)
Max Activating Token Index: 243
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.9458. Min Act: -0.1700
Data Index: 3290893 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.9146. Min Act: -0.1700
Data Index: 5062994 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.8833. Min Act: -0.1699
Data Index: 4466927 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.8833. Min Act: -0.1700
Data Index: 8169504 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.8208. Min Act: -0.1700
Data Index: 6234880 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.7896. Min Act: -0.1700
Data Index: 2401389 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.7896. Min Act: -0.1700
Data Index: 3424119 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.7896. Min Act: -0.1700
Data Index: 5456601 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.7896. Min Act: -0.1700
Data Index: 6511648 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.7583. Min Act: -0.1700
Data Index: 2218445 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.7583. Min Act: -0.1700
Data Index: 7154127 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.6646. Min Act: -0.1700
Data Index: 3423357 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.6333. Min Act: -0.1700
Data Index: 8170900 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.6333. Min Act: -0.1700
Data Index: 1837841 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.6333. Min Act: -0.1700
Data Index: 2332187 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1021. Min Range: -7.1021
Max Act: 6.6333. Min Act: -0.1700
Data Index: 3652789 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19