Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3550 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0097. Min Range: -6.0097
Max Act: 6.0097. Min Act: -0.1700
Data Index: 280399 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.9784. Min Act: -0.1700
Data Index: 7623476 (Open Web Text)
Max Activating Token Index: 367
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.9472. Min Act: -0.1700
Data Index: 1544537 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8534. Min Act: -0.1700
Data Index: 3042394 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8534. Min Act: -0.1700
Data Index: 2431653 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8847. Min Act: -0.1700
Data Index: 5806817 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8534. Min Act: -0.1700
Data Index: 1997515 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8534. Min Act: -0.1700
Data Index: 1285863 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8534. Min Act: -0.1700
Data Index: 1791580 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8222. Min Act: -0.1700
Data Index: 2268766 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8222. Min Act: -0.1700
Data Index: 2359935 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.8222. Min Act: -0.1700
Data Index: 3545507 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7909. Min Act: -0.1700
Data Index: 4309652 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7909. Min Act: -0.1700
Data Index: 7691775 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7909. Min Act: -0.1700
Data Index: 4558456 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7597. Min Act: -0.1700
Data Index: 6069804 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7597. Min Act: -0.1700
Data Index: 156698 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7909. Min Act: -0.1700
Data Index: 3938846 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7597. Min Act: -0.1700
Data Index: 4884921 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0097. Min Range: -6.0097
Max Act: 5.7284. Min Act: -0.1700
Data Index: 6600101 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #19