Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4840 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.0347. Min Range: -3.0347
Max Act: 3.0347. Min Act: -0.1700
Data Index: 5383754 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.0347. Min Range: -3.0347
Max Act: 3.0347. Min Act: -0.1700
Data Index: 3480459 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.0347. Min Range: -3.0347
Max Act: 3.0189. Min Act: -0.1700
Data Index: 8240754 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.9873. Min Act: -0.1700
Data Index: 1370921 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.9557. Min Act: -0.1700
Data Index: 8687994 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.9398. Min Act: -0.1700
Data Index: 3873274 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.9557. Min Act: -0.1700
Data Index: 7440009 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.9557. Min Act: -0.1700
Data Index: 8443889 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.9398. Min Act: -0.1700
Data Index: 7387908 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.9240. Min Act: -0.1700
Data Index: 3635521 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.9082. Min Act: -0.1700
Data Index: 1422538 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8923. Min Act: -0.1700
Data Index: 7227368 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8923. Min Act: -0.1700
Data Index: 2538810 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8923. Min Act: -0.1700
Data Index: 6462451 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8923. Min Act: -0.1700
Data Index: 8829509 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8923. Min Act: -0.1700
Data Index: 5994063 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1817776 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8764. Min Act: -0.1700
Data Index: 7150089 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8764. Min Act: -0.1700
Data Index: 1972039 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.0347. Min Range: -3.0347
Max Act: 2.8606. Min Act: -0.1700
Data Index: 5198435 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19