Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2776 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4341. Min Range: -8.4341
Max Act: 8.4341. Min Act: -0.1700
Data Index: 180709 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4341. Min Range: -8.4341
Max Act: 8.4341. Min Act: -0.1700
Data Index: 7482910 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4341. Min Range: -8.4341
Max Act: 8.3716. Min Act: -0.1700
Data Index: 5214946 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4341. Min Range: -8.4341
Max Act: 8.2466. Min Act: -0.1700
Data Index: 5214941 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4341. Min Range: -8.4341
Max Act: 8.1841. Min Act: -0.1700
Data Index: 4201265 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4341. Min Range: -8.4341
Max Act: 8.1528. Min Act: -0.1700
Data Index: 3133886 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4341. Min Range: -8.4341
Max Act: 8.0903. Min Act: -0.1700
Data Index: 5652498 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4341. Min Range: -8.4341
Max Act: 8.0591. Min Act: -0.1700
Data Index: 8828581 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.9028. Min Act: -0.1700
Data Index: 1127358 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.9028. Min Act: -0.1700
Data Index: 6794272 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.8716. Min Act: -0.1700
Data Index: 8733898 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.8716. Min Act: -0.1700
Data Index: 983341 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.8091. Min Act: -0.1700
Data Index: 8483747 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.8716. Min Act: -0.1700
Data Index: 5760311 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.8091. Min Act: -0.1700
Data Index: 845052 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.8091. Min Act: -0.1700
Data Index: 4782943 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.7778. Min Act: -0.1700
Data Index: 2508381 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.7778. Min Act: -0.1700
Data Index: 5026724 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.7778. Min Act: -0.1700
Data Index: 6581258 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4341. Min Range: -8.4341
Max Act: 7.7778. Min Act: -0.1700
Data Index: 5476289 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #19