Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3500 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.3662. Min Act: -0.1700
Data Index: 2859107 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.3037. Min Act: -0.1700
Data Index: 8180445 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.2412. Min Act: -0.1700
Data Index: 67931 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.1787. Min Act: -0.1700
Data Index: 674934 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.1162. Min Act: -0.1700
Data Index: 5785472 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.1162. Min Act: -0.1700
Data Index: 7431647 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.0537. Min Act: -0.1700
Data Index: 2572724 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.1162. Min Act: -0.1700
Data Index: 912108 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.1162. Min Act: -0.1700
Data Index: 3002775 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.1162. Min Act: -0.1700
Data Index: 1773806 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.0537. Min Act: -0.1700
Data Index: 3804346 (Open Web Text)
Max Activating Token Index: 437
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.0537. Min Act: -0.1700
Data Index: 392133 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3662. Min Range: -9.3662
Max Act: 8.9912. Min Act: -0.1700
Data Index: 7832629 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3662. Min Range: -9.3662
Max Act: 8.9912. Min Act: -0.1700
Data Index: 7916603 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3662. Min Range: -9.3662
Max Act: 8.9287. Min Act: -0.1700
Data Index: 330639 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3662. Min Range: -9.3662
Max Act: 8.9912. Min Act: -0.1700
Data Index: 6280391 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3662. Min Range: -9.3662
Max Act: 8.9912. Min Act: -0.1700
Data Index: 4413148 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3662. Min Range: -9.3662
Max Act: 9.0537. Min Act: -0.1700
Data Index: 157864 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3662. Min Range: -9.3662
Max Act: 8.9287. Min Act: -0.1700
Data Index: 6040530 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3662. Min Range: -9.3662
Max Act: 8.9287. Min Act: -0.1700
Data Index: 3846162 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #19