Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2823 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6939. Min Act: -0.1700
Data Index: 5257726 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6858. Min Act: -0.1700
Data Index: 109733 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6615. Min Act: -0.1700
Data Index: 7647045 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6615. Min Act: -0.1700
Data Index: 5186366 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6535. Min Act: -0.1700
Data Index: 5754935 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6455. Min Act: -0.1690
Data Index: 1942199 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6455. Min Act: -0.1700
Data Index: 1330505 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6535. Min Act: -0.1700
Data Index: 1954595 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6535. Min Act: -0.1700
Data Index: 2592522 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6535. Min Act: -0.1700
Data Index: 3323358 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6375. Min Act: -0.1700
Data Index: 2733694 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6375. Min Act: -0.1700
Data Index: 708258 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6375. Min Act: -0.1700
Data Index: 7831870 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6295. Min Act: -0.1700
Data Index: 1779036 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6295. Min Act: -0.1700
Data Index: 5440978 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6215. Min Act: -0.1700
Data Index: 7064305 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6295. Min Act: -0.1699
Data Index: 4653077 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6295. Min Act: -0.1700
Data Index: 2972309 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6215. Min Act: -0.1700
Data Index: 1471430 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.6939. Min Range: -0.6939
Max Act: 0.6215. Min Act: -0.1700
Data Index: 5973752 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #19