Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2363 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.8111. Min Act: -0.1700
Data Index: 7306914 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.8111. Min Act: -0.1700
Data Index: 6719575 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.8111. Min Act: -0.1700
Data Index: 1282076 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.7798. Min Act: -0.1700
Data Index: 4894416 (Open Web Text)
Max Activating Token Index: 211
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.7798. Min Act: -0.1700
Data Index: 7406885 (Open Web Text)
Max Activating Token Index: 1006
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.7485. Min Act: -0.1700
Data Index: 1588770 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.7485. Min Act: -0.1700
Data Index: 118385 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.7485. Min Act: -0.1700
Data Index: 3474055 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.7485. Min Act: -0.1700
Data Index: 823130 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6860. Min Act: -0.1700
Data Index: 1933658 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.7172. Min Act: -0.1700
Data Index: 6894796 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6860. Min Act: -0.1700
Data Index: 6793191 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.7172. Min Act: -0.1700
Data Index: 6036029 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6860. Min Act: -0.1700
Data Index: 4457867 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6390. Min Act: -0.1700
Data Index: 4948986 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6390. Min Act: -0.1700
Data Index: 5409672 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6860. Min Act: -0.1700
Data Index: 7828594 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6703. Min Act: -0.1697
Data Index: 8059718 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6547. Min Act: -0.1700
Data Index: 2358549 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8111. Min Range: -3.8111
Max Act: 3.6547. Min Act: -0.1700
Data Index: 900770 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19