Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4271 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0230. Min Range: -9.0230
Max Act: 9.0230. Min Act: -0.1700
Data Index: 601073 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0230. Min Range: -9.0230
Max Act: 9.0230. Min Act: -0.1700
Data Index: 6820697 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.8980. Min Act: -0.1700
Data Index: 8380723 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.9605. Min Act: -0.1700
Data Index: 8676603 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.8355. Min Act: -0.1700
Data Index: 2536915 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.8980. Min Act: -0.1700
Data Index: 4357825 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.8980. Min Act: -0.1700
Data Index: 597973 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.8355. Min Act: -0.1700
Data Index: 4685546 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.7730. Min Act: -0.1700
Data Index: 7200591 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.7730. Min Act: -0.1700
Data Index: 2567331 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.7730. Min Act: -0.1700
Data Index: 3680991 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.7730. Min Act: -0.1700
Data Index: 1232557 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.7105. Min Act: -0.1700
Data Index: 2760222 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.7105. Min Act: -0.1700
Data Index: 3646230 (Open Web Text)
Max Activating Token Index: 588
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.7105. Min Act: -0.1700
Data Index: 452515 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.7105. Min Act: -0.1700
Data Index: 5087845 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.6480. Min Act: -0.1700
Data Index: 513722 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.6480. Min Act: -0.1700
Data Index: 3941047 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.6480. Min Act: -0.1700
Data Index: 6455317 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0230. Min Range: -9.0230
Max Act: 8.6480. Min Act: -0.1700
Data Index: 5706712 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #19