Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2004 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6611. Min Range: -6.6611
Max Act: 6.6611. Min Act: -0.1700
Data Index: 4113236 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6611. Min Range: -6.6611
Max Act: 6.2861. Min Act: -0.1700
Data Index: 2264383 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6611. Min Range: -6.6611
Max Act: 6.0986. Min Act: -0.1700
Data Index: 2040526 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.9736. Min Act: -0.1700
Data Index: 4236527 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.8486. Min Act: -0.1700
Data Index: 1000207 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.8486. Min Act: -0.1700
Data Index: 4943118 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.8173. Min Act: -0.1700
Data Index: 7042595 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7861. Min Act: -0.1700
Data Index: 8070160 (Open Web Text)
Max Activating Token Index: 63
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7861. Min Act: -0.1700
Data Index: 6578944 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7548. Min Act: -0.1700
Data Index: 119688 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7548. Min Act: -0.1700
Data Index: 119690 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7548. Min Act: -0.1700
Data Index: 119704 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.6923. Min Act: -0.1700
Data Index: 6387206 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7236. Min Act: -0.1700
Data Index: 119692 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7236. Min Act: -0.1700
Data Index: 6401261 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7548. Min Act: -0.1700
Data Index: 1210062 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7236. Min Act: -0.1700
Data Index: 6150722 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.7236. Min Act: -0.1700
Data Index: 4421765 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.6923. Min Act: -0.1700
Data Index: 5857445 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6611. Min Range: -6.6611
Max Act: 5.6611. Min Act: -0.1700
Data Index: 1927059 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #19