Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2383 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.1104. Min Range: -10.1104
Max Act: 10.1104. Min Act: -0.1700
Data Index: 922543 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.9854. Min Act: -0.1700
Data Index: 3783362 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.9229. Min Act: -0.1700
Data Index: 3254171 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.8604. Min Act: -0.1700
Data Index: 7779554 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.6729. Min Act: -0.1700
Data Index: 14947 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.5479. Min Act: -0.1700
Data Index: 7858370 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.6104. Min Act: -0.1700
Data Index: 1603933 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.5479. Min Act: -0.1700
Data Index: 8150825 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.4854. Min Act: -0.1700
Data Index: 3906691 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.4229. Min Act: -0.1700
Data Index: 6691753 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.4229. Min Act: -0.1700
Data Index: 479961 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.4229. Min Act: -0.1700
Data Index: 7470901 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.4229. Min Act: -0.1700
Data Index: 5495206 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.4229. Min Act: -0.1700
Data Index: 4041979 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.3604. Min Act: -0.1700
Data Index: 2656007 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.3604. Min Act: -0.1700
Data Index: 7542653 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.2979. Min Act: -0.1700
Data Index: 3000720 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.2979. Min Act: -0.1700
Data Index: 7222914 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.2979. Min Act: -0.1700
Data Index: 490543 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.1104. Min Range: -10.1104
Max Act: 9.2979. Min Act: -0.1700
Data Index: 6938335 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #19