Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4366 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.5850. Min Act: -0.1700
Data Index: 1796998 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.5538. Min Act: -0.1700
Data Index: 4216909 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.5538. Min Act: -0.1700
Data Index: 1655187 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.5225. Min Act: -0.1700
Data Index: 7918840 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.5225. Min Act: -0.1700
Data Index: 2698175 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4913. Min Act: -0.1700
Data Index: 8288842 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.5538. Min Act: -0.1700
Data Index: 4378271 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4913. Min Act: -0.1700
Data Index: 1461291 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4913. Min Act: -0.1700
Data Index: 7876869 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4913. Min Act: -0.1700
Data Index: 4923643 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 7654132 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4913. Min Act: -0.1700
Data Index: 7539719 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4913. Min Act: -0.1700
Data Index: 1976292 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 6185615 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 7356466 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4288. Min Act: -0.1700
Data Index: 6054957 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 4028844 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4600. Min Act: -0.1700
Data Index: 2676119 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4288. Min Act: -0.1700
Data Index: 4143020 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.5850. Min Range: -4.5850
Max Act: 4.4288. Min Act: -0.1700
Data Index: 6101427 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #19