Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4728 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0149. Min Range: -6.0149
Max Act: 6.0149. Min Act: -0.1700
Data Index: 2818803 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.9836. Min Act: -0.1700
Data Index: 6409219 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.9211. Min Act: -0.1700
Data Index: 5115263 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.9211. Min Act: -0.1700
Data Index: 3462189 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.8899. Min Act: -0.1700
Data Index: 2536141 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.8899. Min Act: -0.1700
Data Index: 6144641 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.8586. Min Act: -0.1700
Data Index: 1348051 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7961. Min Act: -0.1700
Data Index: 3863116 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.8274. Min Act: -0.1700
Data Index: 3787092 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7961. Min Act: -0.1700
Data Index: 7345632 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7961. Min Act: -0.1700
Data Index: 1057976 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7961. Min Act: -0.1700
Data Index: 1486107 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7961. Min Act: -0.1700
Data Index: 4787925 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7961. Min Act: -0.1700
Data Index: 2502437 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7961. Min Act: -0.1700
Data Index: 1438523 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7961. Min Act: -0.1700
Data Index: 5973404 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.8274. Min Act: -0.1700
Data Index: 1042564 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7649. Min Act: -0.1700
Data Index: 3445678 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7649. Min Act: -0.1700
Data Index: 864372 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0149. Min Range: -6.0149
Max Act: 5.7649. Min Act: -0.1700
Data Index: 1456734 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #19