Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3073 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1606. Min Range: -5.1606
Max Act: 5.1606. Min Act: -0.1700
Data Index: 5741701 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1606. Min Range: -5.1606
Max Act: 5.0981. Min Act: -0.1700
Data Index: 8645535 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.9731. Min Act: -0.1700
Data Index: 7079034 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.9731. Min Act: -0.1700
Data Index: 5907673 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.9418. Min Act: -0.1700
Data Index: 4235756 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.9106. Min Act: -0.1700
Data Index: 4102337 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.9106. Min Act: -0.1700
Data Index: 5964186 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8793. Min Act: -0.1700
Data Index: 1521598 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8793. Min Act: -0.1700
Data Index: 8466047 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8168. Min Act: -0.1700
Data Index: 3931039 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8793. Min Act: -0.1700
Data Index: 6643804 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8481. Min Act: -0.1700
Data Index: 722743 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8168. Min Act: -0.1700
Data Index: 2272032 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8168. Min Act: -0.1700
Data Index: 2222963 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8168. Min Act: -0.1700
Data Index: 103298 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8168. Min Act: -0.1700
Data Index: 985645 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8168. Min Act: -0.1700
Data Index: 8701270 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.8481. Min Act: -0.1700
Data Index: 3648489 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.7543. Min Act: -0.1700
Data Index: 5573904 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1606. Min Range: -5.1606
Max Act: 4.7543. Min Act: -0.1700
Data Index: 7468336 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #19