Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 646 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.6586. Min Range: -6.6586
Max Act: 6.6586. Min Act: -0.1700
Data Index: 10326 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6586. Min Range: -6.6586
Max Act: 6.0023. Min Act: -0.1700
Data Index: 6525076 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.9711. Min Act: -0.1700
Data Index: 4820899 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.9398. Min Act: -0.1700
Data Index: 600128 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.9398. Min Act: -0.1700
Data Index: 5887873 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.9086. Min Act: -0.1700
Data Index: 6217178 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.8773. Min Act: -0.1700
Data Index: 5581324 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.8773. Min Act: -0.1700
Data Index: 3834591 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.8773. Min Act: -0.1700
Data Index: 2875444 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.8773. Min Act: -0.1700
Data Index: 6433500 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.9086. Min Act: -0.1700
Data Index: 7475757 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.8461. Min Act: -0.1700
Data Index: 818633 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.8148. Min Act: -0.1700
Data Index: 1250226 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.7836. Min Act: -0.1700
Data Index: 6433501 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.7836. Min Act: -0.1700
Data Index: 5816831 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.7836. Min Act: -0.1700
Data Index: 4971764 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.7836. Min Act: -0.1700
Data Index: 8799727 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.7211. Min Act: -0.1700
Data Index: 3531772 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.7211. Min Act: -0.1700
Data Index: 5711352 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6586. Min Range: -6.6586
Max Act: 5.7211. Min Act: -0.1700
Data Index: 5390073 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #19