Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4223 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.9849. Min Act: -0.1700
Data Index: 3483324 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.9849. Min Act: -0.1700
Data Index: 6594499 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.8755. Min Act: -0.1700
Data Index: 3309026 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.8755. Min Act: -0.1700
Data Index: 5688164 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.7973. Min Act: -0.1700
Data Index: 872841 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.8129. Min Act: -0.1700
Data Index: 4288646 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.7660. Min Act: -0.1700
Data Index: 3661069 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.7660. Min Act: -0.1700
Data Index: 7633842 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.7504. Min Act: -0.1700
Data Index: 2937264 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.7191. Min Act: -0.1700
Data Index: 6378826 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.7035. Min Act: -0.1700
Data Index: 2991982 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.7191. Min Act: -0.1700
Data Index: 7320428 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.7035. Min Act: -0.1700
Data Index: 8582890 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.6878. Min Act: -0.1700
Data Index: 49576 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.6565. Min Act: -0.1700
Data Index: 5642574 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.6722. Min Act: -0.1700
Data Index: 7812984 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.6722. Min Act: -0.1700
Data Index: 3321331 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.6722. Min Act: -0.1700
Data Index: 784252 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.6409. Min Act: -0.1700
Data Index: 6735918 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9849. Min Range: -3.9849
Max Act: 3.6565. Min Act: -0.1700
Data Index: 5311088 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #19