Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2528 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.9112. Min Act: -0.1700
Data Index: 8453109 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.8487. Min Act: -0.1700
Data Index: 4412382 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.8175. Min Act: -0.1700
Data Index: 8689246 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.8175. Min Act: -0.1699
Data Index: 6745424 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.7550. Min Act: -0.1700
Data Index: 587969 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.7550. Min Act: -0.1700
Data Index: 3602892 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.7237. Min Act: -0.1700
Data Index: 6581996 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.7237. Min Act: -0.1700
Data Index: 4727912 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.7237. Min Act: -0.1700
Data Index: 2297296 (Open Web Text)
Max Activating Token Index: 374
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.7237. Min Act: -0.1700
Data Index: 2241926 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.7550. Min Act: -0.1700
Data Index: 3698853 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6925. Min Act: -0.1700
Data Index: 7982571 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6612. Min Act: -0.1700
Data Index: 417235 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6612. Min Act: -0.1700
Data Index: 5291872 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6612. Min Act: -0.1700
Data Index: 6772444 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6612. Min Act: -0.1700
Data Index: 7529874 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6300. Min Act: -0.1700
Data Index: 7584128 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6300. Min Act: -0.1699
Data Index: 7021566 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6612. Min Act: -0.1700
Data Index: 3187923 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9112. Min Range: -6.9112
Max Act: 6.6300. Min Act: -0.1700
Data Index: 7584127 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #19