Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1708 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1809. Min Range: -4.1809
Max Act: 4.1809. Min Act: -0.1700
Data Index: 3791239 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1809. Min Range: -4.1809
Max Act: 4.0872. Min Act: -0.1700
Data Index: 4691718 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1809. Min Range: -4.1809
Max Act: 4.0247. Min Act: -0.1700
Data Index: 8039816 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1809. Min Range: -4.1809
Max Act: 4.0247. Min Act: -0.1700
Data Index: 3133009 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9621. Min Act: -0.1700
Data Index: 8431728 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1809. Min Range: -4.1809
Max Act: 4.0247. Min Act: -0.1700
Data Index: 1862868 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9934. Min Act: -0.1700
Data Index: 4599890 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9934. Min Act: -0.1700
Data Index: 712196 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9621. Min Act: -0.1700
Data Index: 7812320 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9934. Min Act: -0.1700
Data Index: 5702054 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9934. Min Act: -0.1700
Data Index: 3192941 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9621. Min Act: -0.1700
Data Index: 4574799 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9621. Min Act: -0.1700
Data Index: 3127766 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9309. Min Act: -0.1700
Data Index: 2298149 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9621. Min Act: -0.1700
Data Index: 1192148 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9934. Min Act: -0.1700
Data Index: 3450369 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.8996. Min Act: -0.1700
Data Index: 611904 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9621. Min Act: -0.1700
Data Index: 7398789 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.9309. Min Act: -0.1700
Data Index: 3731787 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1809. Min Range: -4.1809
Max Act: 3.8996. Min Act: -0.1700
Data Index: 868575 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #19