Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2904 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4160. Min Range: -9.4160
Max Act: 9.4160. Min Act: -0.1700
Data Index: 2647255 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4160. Min Range: -9.4160
Max Act: 9.2910. Min Act: -0.1700
Data Index: 5497712 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4160. Min Range: -9.4160
Max Act: 9.1660. Min Act: -0.1700
Data Index: 6102076 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.9785. Min Act: -0.1700
Data Index: 610708 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.9785. Min Act: -0.1700
Data Index: 8559647 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.9160. Min Act: -0.1700
Data Index: 2117892 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.9160. Min Act: -0.1700
Data Index: 7579269 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.8535. Min Act: -0.1700
Data Index: 1545260 (Open Web Text)
Max Activating Token Index: 667
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.8535. Min Act: -0.1700
Data Index: 8333579 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.7910. Min Act: -0.1700
Data Index: 326322 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.7910. Min Act: -0.1700
Data Index: 1833393 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.7910. Min Act: -0.1700
Data Index: 6762987 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.7285. Min Act: -0.1700
Data Index: 7924531 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.7285. Min Act: -0.1700
Data Index: 8776740 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.7910. Min Act: -0.1700
Data Index: 6597238 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.6660. Min Act: -0.1700
Data Index: 4115526 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.6035. Min Act: -0.1700
Data Index: 2671371 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.6035. Min Act: -0.1700
Data Index: 249754 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.6035. Min Act: -0.1700
Data Index: 6309902 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4160. Min Range: -9.4160
Max Act: 8.6035. Min Act: -0.1700
Data Index: 5756589 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #19