Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3077 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.9672. Min Act: -0.1700
Data Index: 8726903 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.9359. Min Act: -0.1700
Data Index: 2262544 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.9047. Min Act: -0.1700
Data Index: 574160 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.8734. Min Act: -0.1700
Data Index: 2542121 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.8109. Min Act: -0.1700
Data Index: 574149 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.8109. Min Act: -0.1700
Data Index: 8255275 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7484. Min Act: -0.1700
Data Index: 1086922 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7797. Min Act: -0.1700
Data Index: 4032091 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7797. Min Act: -0.1700
Data Index: 1266120 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7172. Min Act: -0.1700
Data Index: 574151 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7484. Min Act: -0.1700
Data Index: 8196345 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7484. Min Act: -0.1700
Data Index: 3665904 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7484. Min Act: -0.1700
Data Index: 7391033 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7484. Min Act: -0.1700
Data Index: 3688941 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7484. Min Act: -0.1700
Data Index: 8539762 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7172. Min Act: -0.1700
Data Index: 380861 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7172. Min Act: -0.1700
Data Index: 1131493 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7172. Min Act: -0.1700
Data Index: 1940598 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7172. Min Act: -0.1700
Data Index: 3721627 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9672. Min Range: -4.9672
Max Act: 4.7484. Min Act: -0.1700
Data Index: 7023900 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19