Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5936 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0915. Min Range: -9.0915
Max Act: 9.0915. Min Act: -0.1700
Data Index: 2611438 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0915. Min Range: -9.0915
Max Act: 9.0290. Min Act: -0.1700
Data Index: 2611436 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.9040. Min Act: -0.1700
Data Index: 2699119 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.9040. Min Act: -0.1700
Data Index: 2611437 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.8415. Min Act: -0.1700
Data Index: 1397153 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.8415. Min Act: -0.1700
Data Index: 7532755 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.7790. Min Act: -0.1700
Data Index: 2083026 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.7165. Min Act: -0.1700
Data Index: 1397152 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.7165. Min Act: -0.1700
Data Index: 1662963 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.6540. Min Act: -0.1700
Data Index: 1711473 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.6540. Min Act: -0.1700
Data Index: 4406984 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 1692542 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 2708812 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 495745 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 2083032 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 3593931 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 5569212 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 6010472 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 4203193 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0915. Min Range: -9.0915
Max Act: 8.5915. Min Act: -0.1700
Data Index: 4901373 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19