Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4472 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.8700. Min Act: -0.1700
Data Index: 3262316 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.6200. Min Act: -0.1700
Data Index: 8691946 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.4950. Min Act: -0.1700
Data Index: 3758935 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.3700. Min Act: -0.1700
Data Index: 4966165 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.3700. Min Act: -0.1700
Data Index: 2474227 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.3075. Min Act: -0.1700
Data Index: 4587882 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.2450. Min Act: -0.1700
Data Index: 8691943 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.2450. Min Act: -0.1700
Data Index: 2763953 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1825. Min Act: -0.1700
Data Index: 7075751 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1825. Min Act: -0.1700
Data Index: 3970371 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1825. Min Act: -0.1700
Data Index: 3883013 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1825. Min Act: -0.1700
Data Index: 4868097 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1200. Min Act: -0.1700
Data Index: 2657673 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1200. Min Act: -0.1700
Data Index: 1963994 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1825. Min Act: -0.1700
Data Index: 2486155 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1200. Min Act: -0.1700
Data Index: 3884320 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.1200. Min Act: -0.1700
Data Index: 4617662 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8700. Min Range: -8.8700
Max Act: 8.0575. Min Act: -0.1700
Data Index: 944375 (Open Web Text)
Max Activating Token Index: 57
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8700. Min Range: -8.8700
Max Act: 7.9950. Min Act: -0.1700
Data Index: 4508789 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8700. Min Range: -8.8700
Max Act: 7.9950. Min Act: -0.1700
Data Index: 12950 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #19