Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5171 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.9419. Min Act: -0.1700
Data Index: 5571432 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.5669. Min Act: -0.1700
Data Index: 5811025 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.4731. Min Act: -0.1700
Data Index: 5783037 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.4106. Min Act: -0.1700
Data Index: 8353692 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.3169. Min Act: -0.1700
Data Index: 1108132 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.2856. Min Act: -0.1700
Data Index: 8517435 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.2544. Min Act: -0.1700
Data Index: 8182675 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.2231. Min Act: -0.1700
Data Index: 7294017 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.1606. Min Act: -0.1700
Data Index: 3365412 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.1606. Min Act: -0.1700
Data Index: 6413062 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.1606. Min Act: -0.1700
Data Index: 4023542 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.1294. Min Act: -0.1700
Data Index: 5453366 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.1294. Min Act: -0.1700
Data Index: 3107346 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.0981. Min Act: -0.1700
Data Index: 777424 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.0981. Min Act: -0.1700
Data Index: 1222399 (Open Web Text)
Max Activating Token Index: 354
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.0356. Min Act: -0.1700
Data Index: 4030382 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.0356. Min Act: -0.1700
Data Index: 4350966 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.0669. Min Act: -0.1700
Data Index: 3014106 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.0669. Min Act: -0.1700
Data Index: 1848177 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9419. Min Range: -5.9419
Max Act: 5.0669. Min Act: -0.1700
Data Index: 8806634 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #19