Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4216 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2621. Min Range: -7.2621
Max Act: 7.2621. Min Act: -0.1700
Data Index: 3125669 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2621. Min Range: -7.2621
Max Act: 7.1683. Min Act: -0.1700
Data Index: 97275 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.9808. Min Act: -0.1700
Data Index: 6680609 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.9496. Min Act: -0.1700
Data Index: 6695463 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.9183. Min Act: -0.1700
Data Index: 7747202 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.9183. Min Act: -0.1700
Data Index: 6987077 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.8871. Min Act: -0.1700
Data Index: 8210289 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.9183. Min Act: -0.1700
Data Index: 7788612 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.8558. Min Act: -0.1700
Data Index: 5732317 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.8246. Min Act: -0.1700
Data Index: 2959206 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.8246. Min Act: -0.1700
Data Index: 4316997 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.7933. Min Act: -0.1700
Data Index: 929982 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.7933. Min Act: -0.1700
Data Index: 4494652 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.7933. Min Act: -0.1700
Data Index: 8551929 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.7308. Min Act: -0.1700
Data Index: 6986432 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.7308. Min Act: -0.1700
Data Index: 1824346 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.7308. Min Act: -0.1700
Data Index: 4244653 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.7308. Min Act: -0.1700
Data Index: 7815613 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.6683. Min Act: -0.1700
Data Index: 5996260 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2621. Min Range: -7.2621
Max Act: 6.6996. Min Act: -0.1700
Data Index: 6343816 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #19