Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2646 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.3537. Min Act: -0.1700
Data Index: 2808089 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.2633. Min Act: -0.1653
Data Index: 7367379 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.1388. Min Act: -0.1700
Data Index: 5059851 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0970. Min Act: -0.1698
Data Index: 4358027 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0635. Min Act: -0.1689
Data Index: 8633576 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0635. Min Act: -0.1700
Data Index: 5508755 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0467. Min Act: -0.1698
Data Index: 8608073 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0383. Min Act: -0.1700
Data Index: 893802 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0383. Min Act: -0.1658
Data Index: 2233022 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0383. Min Act: -0.1700
Data Index: 8375737 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0383. Min Act: -0.1699
Data Index: 972738 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0551. Min Act: -0.1700
Data Index: 1402934 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0214. Min Act: -0.1700
Data Index: 7422611 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0214. Min Act: -0.1700
Data Index: 7073335 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0298. Min Act: -0.1700
Data Index: 5618074 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0214. Min Act: -0.1695
Data Index: 1439715 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0298. Min Act: -0.1700
Data Index: 1960295 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0383. Min Act: -0.1700
Data Index: 3698191 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0045. Min Act: -0.1698
Data Index: 1273077 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.3537. Min Range: -2.3537
Max Act: 2.0214. Min Act: -0.1700
Data Index: 8507841 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #19