Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3426 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3915. Min Range: -9.3915
Max Act: 9.3915. Min Act: -0.1700
Data Index: 2207217 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3915. Min Range: -9.3915
Max Act: 9.2040. Min Act: -0.1700
Data Index: 4598578 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3915. Min Range: -9.3915
Max Act: 9.2040. Min Act: -0.1700
Data Index: 3807464 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3915. Min Range: -9.3915
Max Act: 9.0790. Min Act: -0.1700
Data Index: 5689743 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.9540. Min Act: -0.1700
Data Index: 7285516 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.9540. Min Act: -0.1700
Data Index: 4549626 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.9540. Min Act: -0.1700
Data Index: 5157619 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.9540. Min Act: -0.1700
Data Index: 1407128 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.9540. Min Act: -0.1700
Data Index: 899898 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.8915. Min Act: -0.1700
Data Index: 5454806 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.8915. Min Act: -0.1700
Data Index: 7882181 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.8915. Min Act: -0.1700
Data Index: 6092220 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.8915. Min Act: -0.1700
Data Index: 6685932 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.8290. Min Act: -0.1700
Data Index: 6710268 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.9540. Min Act: -0.1700
Data Index: 266459 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.8290. Min Act: -0.1700
Data Index: 2371847 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.8290. Min Act: -0.1700
Data Index: 1414976 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.8290. Min Act: -0.1700
Data Index: 5141125 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.7665. Min Act: -0.1700
Data Index: 5285591 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3915. Min Range: -9.3915
Max Act: 8.7665. Min Act: -0.1700
Data Index: 1011266 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #19