Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 583 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.3901. Min Act: -0.1700
Data Index: 1240033 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.3276. Min Act: -0.1700
Data Index: 6150466 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.2651. Min Act: -0.1700
Data Index: 3832594 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.2026. Min Act: -0.1700
Data Index: 1281851 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.2026. Min Act: -0.1700
Data Index: 6100789 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.1401. Min Act: -0.1700
Data Index: 1150190 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.0776. Min Act: -0.1700
Data Index: 8583492 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.0776. Min Act: -0.1700
Data Index: 8495907 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.0151. Min Act: -0.1700
Data Index: 6988786 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.0776. Min Act: -0.1700
Data Index: 6988787 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.0776. Min Act: -0.1700
Data Index: 1645857 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.0776. Min Act: -0.1700
Data Index: 1240032 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.0776. Min Act: -0.1700
Data Index: 4112239 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.3901. Min Range: -9.3901
Max Act: 9.0776. Min Act: -0.1700
Data Index: 8115851 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.3901. Min Range: -9.3901
Max Act: 8.8901. Min Act: -0.1700
Data Index: 7804975 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.3901. Min Range: -9.3901
Max Act: 8.8901. Min Act: -0.1700
Data Index: 8242908 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.3901. Min Range: -9.3901
Max Act: 8.8901. Min Act: -0.1700
Data Index: 8581825 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.3901. Min Range: -9.3901
Max Act: 8.7651. Min Act: -0.1700
Data Index: 3831241 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.3901. Min Range: -9.3901
Max Act: 8.7651. Min Act: -0.1700
Data Index: 4785166 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.3901. Min Range: -9.3901
Max Act: 8.7026. Min Act: -0.1700
Data Index: 7957666 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #19