Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 804 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.2261. Min Act: -0.1700
Data Index: 7297064 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.2261. Min Act: -0.1700
Data Index: 889930 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.1949. Min Act: -0.1700
Data Index: 7444324 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.1636. Min Act: -0.1700
Data Index: 7952721 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.1011. Min Act: -0.1700
Data Index: 4465232 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 1202424 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.0386. Min Act: -0.1700
Data Index: 7094947 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.0074. Min Act: -0.1700
Data Index: 2922099 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.9449. Min Act: -0.1700
Data Index: 7553622 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.9761. Min Act: -0.1700
Data Index: 5639049 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2261. Min Range: -6.2261
Max Act: 6.0074. Min Act: -0.1700
Data Index: 5030994 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.9136. Min Act: -0.1700
Data Index: 8565044 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.9761. Min Act: -0.1700
Data Index: 1046091 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.8824. Min Act: -0.1700
Data Index: 4175379 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.9136. Min Act: -0.1700
Data Index: 5582375 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.9136. Min Act: -0.1700
Data Index: 8383232 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.8824. Min Act: -0.1700
Data Index: 5127273 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.9136. Min Act: -0.1700
Data Index: 3125694 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.9136. Min Act: -0.1700
Data Index: 7502931 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2261. Min Range: -6.2261
Max Act: 5.8824. Min Act: -0.1700
Data Index: 4542726 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #19