Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3538 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.8736. Min Act: -0.1700
Data Index: 8082497 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.7486. Min Act: -0.1700
Data Index: 3324551 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.6861. Min Act: -0.1700
Data Index: 4379391 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.6861. Min Act: -0.1700
Data Index: 7841133 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.6236. Min Act: -0.1700
Data Index: 5782082 (Open Web Text)
Max Activating Token Index: 264
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.6236. Min Act: -0.1700
Data Index: 501229 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.5611. Min Act: -0.1700
Data Index: 7562997 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.5611. Min Act: -0.1700
Data Index: 940950 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.5611. Min Act: -0.1700
Data Index: 8193603 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.4986. Min Act: -0.1700
Data Index: 595441 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.4361. Min Act: -0.1700
Data Index: 1990299 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.4986. Min Act: -0.1700
Data Index: 125829 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.4986. Min Act: -0.1700
Data Index: 3027527 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.5611. Min Act: -0.1700
Data Index: 6380806 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.4361. Min Act: -0.1700
Data Index: 1783746 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.4361. Min Act: -0.1700
Data Index: 7365074 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.3736. Min Act: -0.1700
Data Index: 3437805 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.3736. Min Act: -0.1700
Data Index: 4432427 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.3736. Min Act: -0.1700
Data Index: 4474859 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8736. Min Range: -8.8736
Max Act: 8.3736. Min Act: -0.1700
Data Index: 2209816 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19