Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3646 in Layer 34
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0706. Min Range: -7.0706
Max Act: 7.0706. Min Act: -0.1700
Data Index: 584244 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0706. Min Range: -7.0706
Max Act: 7.0081. Min Act: -0.1700
Data Index: 1018286 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.9768. Min Act: -0.1700
Data Index: 3784736 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.8831. Min Act: -0.1700
Data Index: 1890585 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.8831. Min Act: -0.1700
Data Index: 2535757 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.8831. Min Act: -0.1700
Data Index: 1745510 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.8206. Min Act: -0.1700
Data Index: 4330128 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.7893. Min Act: -0.1700
Data Index: 6680219 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.7893. Min Act: -0.1700
Data Index: 8063477 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1193322 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.7268. Min Act: -0.1700
Data Index: 692230 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.7893. Min Act: -0.1700
Data Index: 7236969 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.6956. Min Act: -0.1700
Data Index: 5017 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1940859 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.7268. Min Act: -0.1700
Data Index: 1229589 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.6643. Min Act: -0.1700
Data Index: 4708445 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.6643. Min Act: -0.1700
Data Index: 7631751 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.6331. Min Act: -0.1700
Data Index: 3100730 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.6331. Min Act: -0.1700
Data Index: 2409467 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0706. Min Range: -7.0706
Max Act: 6.6331. Min Act: -0.1700
Data Index: 5896206 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #19