Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 1026 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.0828. Min Range: -6.0828
Max Act: 6.0828. Min Act: -0.1700
Data Index: 3715794 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0828. Min Range: -6.0828
Max Act: 6.0203. Min Act: -0.1700
Data Index: 6953932 (Open Web Text)
Max Activating Token Index: 361
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.7390. Min Act: -0.1700
Data Index: 2872437 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.7703. Min Act: -0.1700
Data Index: 5443204 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.7390. Min Act: -0.1700
Data Index: 6220084 (Open Web Text)
Max Activating Token Index: 414
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.7078. Min Act: -0.1700
Data Index: 971644 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.7078. Min Act: -0.1700
Data Index: 8655835 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.7390. Min Act: -0.1700
Data Index: 993753 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.7078. Min Act: -0.1700
Data Index: 2693044 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.6765. Min Act: -0.1700
Data Index: 5520201 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.6140. Min Act: -0.1700
Data Index: 1701247 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.6453. Min Act: -0.1700
Data Index: 4354191 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.6453. Min Act: -0.1700
Data Index: 4816141 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.6453. Min Act: -0.1700
Data Index: 7143541 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.5828. Min Act: -0.1700
Data Index: 5507150 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.5828. Min Act: -0.1700
Data Index: 5059287 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.6453. Min Act: -0.1700
Data Index: 8501294 (Open Web Text)
Max Activating Token Index: 964
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.5515. Min Act: -0.1700
Data Index: 3355297 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.5515. Min Act: -0.1700
Data Index: 3900257 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0828. Min Range: -6.0828
Max Act: 5.5828. Min Act: -0.1700
Data Index: 3594080 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19