Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1193 in Layer 36
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2591. Min Range: -8.2591
Max Act: 8.2591. Min Act: -0.1700
Data Index: 3637396 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2591. Min Range: -8.2591
Max Act: 8.2591. Min Act: -0.1700
Data Index: 4568987 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2591. Min Range: -8.2591
Max Act: 8.2591. Min Act: -0.1700
Data Index: 7424068 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2591. Min Range: -8.2591
Max Act: 8.1341. Min Act: -0.1700
Data Index: 4616845 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2591. Min Range: -8.2591
Max Act: 8.0716. Min Act: -0.1700
Data Index: 176549 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2591. Min Range: -8.2591
Max Act: 8.0716. Min Act: -0.1700
Data Index: 4459462 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2591. Min Range: -8.2591
Max Act: 8.0716. Min Act: -0.1700
Data Index: 4002112 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.9466. Min Act: -0.1700
Data Index: 7916469 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.9466. Min Act: -0.1700
Data Index: 2170551 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.8841. Min Act: -0.1700
Data Index: 7850797 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.8841. Min Act: -0.1700
Data Index: 6432112 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.9466. Min Act: -0.1700
Data Index: 8727725 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.8216. Min Act: -0.1700
Data Index: 4993191 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.8216. Min Act: -0.1700
Data Index: 6565574 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.6966. Min Act: -0.1700
Data Index: 201612 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.7591. Min Act: -0.1700
Data Index: 925177 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.7591. Min Act: -0.1700
Data Index: 4679389 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.7591. Min Act: -0.1700
Data Index: 7224564 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.6966. Min Act: -0.1700
Data Index: 6293580 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2591. Min Range: -8.2591
Max Act: 7.7591. Min Act: -0.1700
Data Index: 2748201 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #19