Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1302 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0482. Min Range: -3.0482
Max Act: 3.0482. Min Act: -0.1700
Data Index: 3443304 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0482. Min Range: -3.0482
Max Act: 3.0324. Min Act: -0.1700
Data Index: 1447997 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.9534. Min Act: -0.1700
Data Index: 7754579 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.9375. Min Act: -0.1700
Data Index: 5696853 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.9217. Min Act: -0.1700
Data Index: 563542 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.9217. Min Act: -0.1700
Data Index: 6398417 (Open Web Text)
Max Activating Token Index: 285
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8741. Min Act: -0.1700
Data Index: 1313949 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8900. Min Act: -0.1700
Data Index: 539092 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8741. Min Act: -0.1700
Data Index: 2288368 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8741. Min Act: -0.1700
Data Index: 5988268 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8582. Min Act: -0.1700
Data Index: 6949139 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8424. Min Act: -0.1700
Data Index: 3939153 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8424. Min Act: -0.1700
Data Index: 1503892 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8582. Min Act: -0.1700
Data Index: 4029082 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8582. Min Act: -0.1700
Data Index: 62820 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8424. Min Act: -0.1700
Data Index: 4532130 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8265. Min Act: -0.1700
Data Index: 8246468 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8424. Min Act: -0.1700
Data Index: 8564802 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8424. Min Act: -0.1700
Data Index: 1393930 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0482. Min Range: -3.0482
Max Act: 2.8582. Min Act: -0.1700
Data Index: 2337104 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #19