Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7929. Min Act: -0.1700
Data Index: 3164469 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7929. Min Act: -0.1681
Data Index: 6664807 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7843. Min Act: -0.1700
Data Index: 7345905 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7843. Min Act: -0.1699
Data Index: 2908018 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7671. Min Act: -0.1700
Data Index: 4630473 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7671. Min Act: -0.1700
Data Index: 7112602 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7498. Min Act: -0.1700
Data Index: 1973613 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7584. Min Act: -0.1700
Data Index: 8003163 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7584. Min Act: -0.1700
Data Index: 4783186 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7412. Min Act: -0.1700
Data Index: 64133 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7239. Min Act: -0.1700
Data Index: 5755010 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7325. Min Act: -0.1700
Data Index: 3722070 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7152. Min Act: -0.1700
Data Index: 4118926 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7152. Min Act: -0.1700
Data Index: 8000867 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6892. Min Act: -0.1700
Data Index: 5311459 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7152. Min Act: -0.1700
Data Index: 8513178 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.7065. Min Act: -0.1700
Data Index: 2591425 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6979. Min Act: -0.1700
Data Index: 2618077 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6892. Min Act: -0.1700
Data Index: 3179939 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.7929. Min Range: -1.7929
Max Act: 1.6718. Min Act: -0.1700
Data Index: 732852 (Open Web Text)
Max Activating Token Index: 359
Click toggle to see full text
Truncated
Full Text #19